© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 17902
    Prev
    Next
    INDEX
    Explanations

    medical professionals

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     machinery
    -0.09
     negatives
    -0.08
    enseignement
    -0.08
     babies
    -0.08
    700
    -0.08
     separators
    -0.08
     masterpieces
    -0.08
     enormes
    -0.07
    Zeros
    -0.07
     الحب
    -0.07
    POSITIVE LOGITS
     psychologist
    0.20
     dermatologist
    0.20
     pharmacist
    0.20
     huisarts
    0.18
     médecin
    0.18
     psychiatrist
    0.17
     psychologists
    0.17
     pharmacists
    0.16
     endocr
    0.16
     врачу
    0.16
    Activations Density 0.014%

    No Known Activations