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. 52882
    Prev
    Next
    INDEX
    Explanations

    definition, database

    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
     brought
    -0.08
    朋友圈
    -0.08
     élo
    -0.07
    -place
    -0.07
     trae
    -0.07
     Lup
    -0.07
     collections
    -0.07
    此同时
    -0.07
     Oliver
    -0.07
     کان
    -0.07
    POSITIVE LOGITS
    [Index
    0.09
    <Color
    0.08
    صی
    0.08
     Hicks
    0.08
    уки
    0.07
    िष्य
    0.07
    بية
    0.07
     kag
    0.07
     തിരിച്ച
    0.07
     pis
    0.07
    Activations Density 0.001%

    No Known Activations