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. 77269
    Prev
    Next
    INDEX
    Explanations

    description

    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
    ▀
    -0.07
    virus
    -0.07
     கண
    -0.07
    commun
    -0.07
     premature
    -0.07
     eas
    -0.07
    -defined
    -0.07
    community
    -0.07
    _testing
    -0.07
    fra
    -0.07
    POSITIVE LOGITS
     Driven
    0.09
    /feed
    0.09
     sprzeda
    0.08
     säl
    0.08
    (税込
    0.08
     ginn
    0.08
     Wordpress
    0.08
     ul
    0.08
    ūros
    0.08
     cass
    0.08
    Activations Density 0.004%

    No Known Activations