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. 43139
    Prev
    Next
    INDEX
    Explanations

    format strings

    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
    เมือง
    -0.09
     SWOT
    -0.08
    ธุ
    -0.08
     Thailand
    -0.08
     సంస్థ
    -0.08
     संस्थ
    -0.08
     eleições
    -0.08
     ಸಂಸ್ಥ
    -0.08
     Botswana
    -0.08
     Thesis
    -0.08
    POSITIVE LOGITS
    _printf
    0.11
     nargs
    0.11
    babel
    0.09
    argc
    0.09
     printf
    0.09
    encoding
    0.09
    args
    0.09
    compiler
    0.09
    argument
    0.09
    nprintf
    0.09
    Activations Density 0.004%

    No Known Activations