question
active
question:can-clinical-concepts-be-selectively-steered-without-damaging-unrelated-performance

Can clinical concepts be selectively steered without damaging unrelated performance?

Question about the feasibility of safe concept steering in EEG models.

Source paper

extracted_from
Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
(2026) · William Lehn-Schiøler · Magnus Ruud Kjær · Rahul Thapa · M. Pedersen +9

Neighborhood — ranked by edge-count

Findings (2)

finding

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.