© 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. 23-RESID-POST-AA
    11. 51407
    Prev
    Next
    INDEX
    Explanations

    question and answer pairs

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reaction
    -0.07
     reverse
    -0.07
    表示
    -0.07
     accueille
    -0.07
    heiro
    -0.07
    逆
    -0.07
     louer
    -0.07
    表达
    -0.07
     complains
    -0.07
     хэмж
    -0.07
    POSITIVE LOGITS
     odpowied
    0.34
     ಉತ್ತರ
    0.32
     odgov
    0.32
     उत्तर
    0.31
     જવાબ
    0.31
     Ответ
    0.29
     адказ
    0.29
     ഉത്തര
    0.29
     উত্তর
    0.29
     відпов
    0.28
    Activations Density 0.030%

    No Known Activations