CORTEXA
← Browse
arxivcs.LGcs.AI2026-07-13

Sparse Autoencoders for Interpretable Out-of-Distribution Detection

Ayush Karmacharya, Luke Luschwitz, Lucia Romero, Yanan Niu, Joseph Campbell

Reliable detection of out-of-distribution (OOD) samples is crucial for the safe deployment of machine learning models. Neural networks often produce overconfident predictions for inputs that deviate from their training data, leading to significant degradation in performance. While many OOD detection methods focus on the final output layer, they neglect the rich hierarchical information present in intermediate network layers. This paper introduces a novel approach that leverages sparse autoencoders (SAEs) to learn interpretable features from these intermediate activations. We find that in-distribution (ID) and OOD data activate distinct sets of these sparse features. We propose a new OOD score derived from the cosine similarity between the sparse feature activations of a test sample and the mean activations of ID classes. Our post-hoc detection method not only achieves state-of-the-art performance on standard OOD detection benchmarks, but yields interpretable insights into how distribution shift affects learned representations.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CV2026-06-29

Exploiting Local Flatness for Efficient Out-of-Distribution Detection

Seonghwan Park, Hyunji Jung, Dongyeop Lee, Namhoon Lee

Detecting out-of-distribution (OOD) data is crucial for reliable machine learning deployment. Among detection strategies, post-hoc methods are particularly attractive due to their efficiency, as they operate directly on pre-trained networks without requiring retraining. Within th…

View free PDFSource page
arxivcs.LGcs.AI2026-06-25

Beyond the Hard Budget: Sparsity Regularizers for More Interpretable Top-k Sparse Autoencoders

Nathanaël Jacquier, Maria Vakalopoulou, Mahdi S. Hosseini

Sparse autoencoders (SAEs) have become a leading tool for interpreting the representations of vision foundation models, decomposing their polysemantic activations into a larger set of sparse, more monosemantic features. The Top-$k$ SAE, a now-standard variant, enforces sparsity a…

View free PDFSource page
arxivcs.LGcs.AI2026-07-14

OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning

Emil Mittag, Richard Dazeley, Peter Vamplew

Reliable reinforcement learning (RL) agents must maintain operational integrity amidst sensor malfunctions, dynamic disturbances, and slow environmental shifts. The detection of out-of-distribution conditions is pivotal to determining when an agent's observations, transitions, or…

View free PDFSource page
arxivcs.LGcs.AIcs.CRcs.CVstat.ML2026-07-23

Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration

Vishnu Bindu Balachandran

Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream. We show this adaptation obeys a provable dynamical law. Modelling bank impurity as a generalized Pólya urn, we prove almost-sure convergence to a mean-field equilibrium whose s…

View free PDFSource page
arxivcs.LGcs.AIcs.IT2026-07-02

Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability

Rodrigo Mendoza-Smith

Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m<n$, and inferring a sparse code $\mathbf{x}\in\mathbb{R}^n$ from $\…

View free PDFSource page
arxivcs.LGcs.AI2026-06-29

C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders

Haoran Jin, Xiting Wang, Shijie Ren, Hong Xie, Defu Lian

Sparse Autoencoders (SAEs) are widely used to interpret large language models by decomposing activations into sparse, human-understandable features, but scaling to large dictionaries exposes fundamental challenges. Systematic studies reveal pervasive feature splitting that fragme…

View free PDFSource page