© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75519
    Prev
    Next
    INDEX
    Explanations

    genital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trends
    -0.08
    -able
    -0.07
    Proceed
    -0.07
    続
    -0.07
    -0.07
    eworthy
    -0.07
    -main
    -0.07
     tendencias
    -0.07
    (prefix
    -0.07
     crime
    -0.07
    POSITIVE LOGITS
     يمن
    0.09
     бар
    0.08
     añad
    0.08
     equip
    0.08
     تمن
    0.08
     наполн
    0.08
     blockage
    0.08
     вс
    0.08
     Duck
    0.08
     Hag
    0.08
    Activations Density 0.001%
    No Known Activations