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. 75990
    Prev
    Next
    INDEX
    Explanations

    the

    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
    .byt
    -0.09
     बिट
    -0.08
     толщ
    -0.08
    Attrib
    -0.08
    Connector
    -0.08
    ган
    -0.08
     комментар
    -0.08
    指南
    -0.07
     pratique
    -0.07
     phút
    -0.07
    POSITIVE LOGITS
     tecnológica
    0.08
    Tecn
    0.07
     판매
    0.07
     اپنا
    0.07
    (df
    0.07
    евн
    0.07
    istico
    0.07
    units
    0.07
     Deborah
    0.07
    .Switch
    0.07
    Activations Density 0.008%

    No Known Activations