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. 472
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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
     принос
    -0.08
     há
    -0.08
     有
    -0.07
    ogan
    -0.07
    ilka
    -0.07
    652
    -0.07
     звон
    -0.07
     Byzantine
    -0.07
     Εκ
    -0.07
     contag
    -0.07
    POSITIVE LOGITS
    方式
    0.08
    Rev
    0.08
    ,例如
    0.08
    ridge
    0.07
     projetos
    0.07
     Cab
    0.07
    rev
    0.07
    ,比如
    0.07
     poche
    0.07
     xmlns
    0.07
    Activations Density 0.009%

    No Known Activations