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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11696
    Prev
    Next
    INDEX
    Explanations

    Prices and costs

    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
    िना
    -0.08
    rupt
    -0.07
    (Reg
    -0.07
    pọ
    -0.07
     alej
    -0.07
    REM
    -0.07
     indicada
    -0.07
     Police
    -0.07
     punct
    -0.07
     упражнения
    -0.07
    POSITIVE LOGITS
    成本
    0.11
    利润
    0.10
     себ
    0.10
     belakang
    0.09
    幕后
    0.09
     низ
    0.09
     coûts
    0.09
    _cost
    0.09
     profitability
    0.08
     ખર્ચ
    0.08
    Activations Density 0.032%

    No Known Activations