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. 109559
    Prev
    Next
    INDEX
    Explanations

    Group

    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
    ल्य
    -0.07
    ...',↵
    -0.07
    Gy
    -0.07
     LOV
    -0.06
    .conditions
    -0.06
    wk
    -0.06
    acteur
    -0.06
    SET
    -0.06
    みに
    -0.06
    মাত্র
    -0.06
    POSITIVE LOGITS
     Din
    0.09
     spirited
    0.08
     magaalada
    0.08
    ıştır
    0.08
     निर्�
    0.08
    okal
    0.08
    Din
    0.08
    altet
    0.08
     logo
    0.08
    ஸ
    0.08
    Activations Density 0.000%

    No Known Activations