EEG Abnormality

One of four clinical taxonomy dimensions used to benchmark SAE features

Neighborhood — ranked by edge-count

concept

Clinical Taxonomy
associated_with
The grounding schema comprising abnormality, age, sex, and medication used to interpret SAE features
pathological slow-wave suppression
associated_with
EEG frequency signature of reduced slow-wave activity, obtained as a spectral interpretation of steering.
α-band restoration
associated_with
Restoration of alpha band (8–12 Hz) power in EEG, a physiological signature obtained from spectral decoding.

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.

abnormalityconcept0.823
EEG abnormality concept (e.g., epileptiform activity) used to interpret SAE features.
Medication (EEG)concept0.776
One of four clinical taxonomy dimensions used to benchmark SAE features
Patient Age (EEG)concept0.768
One of four clinical taxonomy dimensions used to benchmark SAE features
EEG Neural Criticality Measurementmethod0.755
Proposed empirical method for testing the criticality prediction in populations reporting stable selflessness
Patient Sex (EEG)concept0.748
One of four clinical taxonomy dimensions used to benchmark SAE features
AI Psychosisconcept0.721
Phenomenon where models uncritically reinforce user delusions about AI consciousness or hidden sentience when persona drifts
EEG Transformer Embeddingsconcept0.720
The internal representations of EEG transformers from which SAE features are extracted
Resting EEG spectral analysis prior to anagram solving revealed right-lateralized hemispheric asymmetry predicting subsequent insight problem-solving (Kounios et al., 2008).finding0.717
Evidence that pre-insight neural states (resting EEG) predict insight; supports role of reflection/mind wandering