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. 111698
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     Residential
    -0.10
    _destroy
    -0.09
     residential
    -0.09
    Residential
    -0.08
    ಮಂತ್ರ
    -0.08
     ನಿವಾಸ
    -0.08
    ্ট
    -0.08
    ]!=
    -0.07
     зерт
    -0.07
     આવતા
    -0.07
    POSITIVE LOGITS
    \Helper
    0.08
     average
    0.08
    .files
    0.07
     chimi
    0.07
     pueda
    0.07
    .avg
    0.07
    46
    0.07
    .Decimal
    0.07
     nearly
    0.07
    哈哈
    0.07
    Activations Density 0.037%

    No Known Activations