Sparse autoencoders

Timeline

1. Oct 8, 2026 · Research paper · 1 source
   RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing
   Leveraging the SSH, we introduce RouterInterp, a method for interpreting expert routing that identifies Sparse Autoencoder features most predictive of routing decisions and produces unified natural language explanations.
2. Oct 8, 2026 · Research paper · 1 source
   Regularized Small Area Estimation with Graph Laplacian Benchmarking priors
   The resulting family includes a Benchmarking Prior that incorporates the benchmarking restrictions without additional regularization across areas, and Single and Multi-View Laplacian Benchmarking Priors that introduce regularization through graph Laplacians constructed from area similarities based on external covariate information.
3. Oct 7, 2026 · Research paper · 1 source
   Disentangling Linguistic and Paralinguistic Information with Routed Sparse Autoencoders
   Self-supervised speech encoders contain linguistic and paralinguistic information in a shared, entangled representation space.
4. Oct 7, 2026 · Research paper · 1 source
   Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
   Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models.
5. Oct 6, 2026 · Research paper · 1 source
   AnyBottle: A Recipe to Only Keep the Concepts You Really Need
   We propose AnyBottle, a single recipe for building compact, task-specific CBMs. AnyBottle assumes only a frozen backbone and an unsupervised concept pool, such as a sparse autoencoder.
6. Oct 6, 2026 · Research paper · 1 source
   Illusory Pattern Perception Drives Spurious Inference in Large Language Models
   Illusory pattern perception is a well-documented human cognitive tendency to infer meaningful relationships in data that is actually random.

Often appears with