Can concept steering interventions on EEG foundation models be made selective rather than globally destructive?

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

• Concept steering experiments identify three distinct operational regimes across clinical concepts in EEG foundation models.finding0.831
  Main empirical finding of the concept steering analysis
• How are clinical concepts represented and steerable in EEG foundation models?question0.821
  Core research question driving the mechanistic investigation.
• Some SAE concept steering interventions act as 'wrecking balls' that collapse global model performance rather than selectively modifying target concepts.claim0.806
  A critical failure mode identified in the paper demonstrating risk of naïve concept steering
• Spectral decoder reveals pathological slow-wave suppression as a frequency signature of concept steering interventions in EEG foundation models.finding0.802
  Links latent space manipulation to known EEG neurophysiology
• Can clinical concepts be selectively steered without damaging unrelated performance?question0.799
  Question about the feasibility of safe concept steering in EEG models.
• What physiologically interpretable frequency signatures correspond to latent concept steering manipulations in EEG foundation models?question0.798
  Research question motivating the spectral decoder methodology
• EEG foundation models achieve state-of-the-art clinical performance yet their internal computations remain opaque, constituting a barrier to clinical trust.claim0.785
  Motivating claim for the entire paper
• Spectral decoder reveals α-band restoration as a frequency signature of concept steering interventions in EEG foundation models.finding0.785
  Links latent space manipulation to known EEG neurophysiology