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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71043
    Prev
    Next
    INDEX
    Explanations

    oric

    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
     Ministers
    -0.07
     ERROR
    -0.07
     fright
    -0.07
     pener
    -0.07
    409
    -0.07
     aggregate
    -0.07
     conto
    -0.06
     outline
    -0.06
     difference
    -0.06
     pagos
    -0.06
    POSITIVE LOGITS
     ощущ
    0.08
    ния
    0.08
     городской
    0.08
     предпри
    0.08
     необы
    0.08
     тес
    0.08
     повыш
    0.08
     обуслов
    0.08
     дальше
    0.08
     сель
    0.08
    Activations Density 0.000%

    No Known Activations