© 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. 71260
    Prev
    Next
    INDEX
    Explanations

    impartial

    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
    aras
    -0.09
     warmth
    -0.08
     ಆರ
    -0.08
    arası
    -0.08
     Vargas
    -0.08
     Sleeve
    -0.08
     Armani
    -0.08
     aure
    -0.07
    ofil
    -0.07
     Diva
    -0.07
    POSITIVE LOGITS
     हित
    0.08
     одинаков
    0.07
    人人
    0.07
    _rules
    0.07
    利益
    0.07
    募集
    0.07
    Granted
    0.07
     identical
    0.07
     symmetric
    0.07
    Eligibility
    0.07
    Activations Density 0.001%

    No Known Activations