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. 15-RESID-POST-AA
    6. 19398
    Prev
    Next
    INDEX
    Explanations

    parser

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     successive
    -0.08
     writings
    -0.07
     বা
    -0.07
    迹
    -0.07
    ংস
    -0.07
    iyay
    -0.07
     reflections
    -0.07
    !!!!!
    -0.07
     তার
    -0.07
     detrimental
    -0.07
    POSITIVE LOGITS
    _args
    0.12
    .xlabel
    0.10
    _kwargs
    0.10
    .Argument
    0.10
    .arg
    0.09
    ಿಕೊಳ್ಳ
    0.09
    .Optional
    0.09
    .describe
    0.09
    Args
    0.09
    .add
    0.09
    Activations Density 0.001%

    No Known Activations