MMODELYST
Papers/Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
PAP

Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders

May 13, 2026

arXiv
Abstract

EEG foundation models achieve state-of-the-art clinical performance, yet the internal computations driving their predictions remain opaque: a barrier to clinical trust. We apply TopK Sparse Autoencoders (SAEs) across three architecturally distinct EEG transformers: SleepFM, REVE, and LaBraM to extract sparse feature dictionaries from their embeddings. By grounding these features in a clinical taxonomy (abnormality, age, sex, and medication), we benchmark monosemanticity and entanglement across architectures. A single hyperparameter procedure, driven by an intrinsic dictionary health audit, transfers robustly across all three architectures. Via concept steering, we introduce a "target vs. off-target" probe area metric to quantify steering selectivity and reveal three operational regimes: selectively steerable, encoded but entangled, and non-encoded. This framework exposes critical representational failures: "wrecking-ball" interventions that collapse global model performance, and clinical entanglements, such as age-pathology confounding, where it is impossible to suppress one concept without corrupting the other. Finally, a spectral decoder maps these interventions back to the amplitude spectrum, translating latent manipulations into physiologically interpretable frequency signatures, such as pathological slow-wave suppression and $α$-band restoration.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
William Lehn-Schiøler, Magnus Ruud Kjær, Rahul Thapa, Magnus Guldberg Pedersen, Anton Mosquera Storgaard, Nick Williams, Radu Gatej, Tue Lehn-Schiøler, Andreas Brink-Kjær, Sadasivan Puthusserypady, Sándor Beniczky, James Zou, Lars Kai Hansen
Your notes (browser-local)
saved
arXiv:2605.13930