Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52914
    Prev
    Next
    INDEX
    Explanations

    breakout

    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
    in
    -0.08
     অপেক্ষ
    -0.08
    daten
    -0.08
    颜色
    -0.08
    Family
    -0.07
     Family
    -0.07
    182
    -0.07
     dekat
    -0.07
    ం
    -0.07
    insic
    -0.07
    POSITIVE LOGITS
    自治区
    0.09
     prm
    0.08
     rije
    0.08
     engagements
    0.08
     shoulders
    0.08
    qqat
    0.08
    ZF
    0.08
     permalink
    0.07
    REFERRED
    0.07
    ठ
    0.07
    Activations Density 0.001%

    No Known Activations