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. 65798
    Prev
    Next
    INDEX
    Explanations

    parse_args

    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
     hela
    -0.07
    Daddy
    -0.07
    หวย
    -0.07
    owej
    -0.07
     crack
    -0.07
     UBS
    -0.07
     chants
    -0.07
    Hill
    -0.07
    สบ
    -0.07
    ave
    -0.07
    POSITIVE LOGITS
    �
    0.09
    _args
    0.08
    /options
    0.08
    Args
    0.08
    (schema
    0.08
     collected
    0.08
    .args
    0.08
    .Argument
    0.08
    ({'
    0.07
    、安全
    0.07
    Activations Density 0.002%

    No Known Activations