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. 111841
    Prev
    Next
    INDEX
    Explanations

    lives

    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
     procedure
    -0.07
     تكون
    -0.07
    ड़ी
    -0.07
    -0.07
    ịch
    -0.07
     if
    -0.07
     cookies
    -0.07
     Procedure
    -0.07
     Elton
    -0.07
     la
    -0.07
    POSITIVE LOGITS
     драм
    0.11
     dramas
    0.10
     drama
    0.09
     Drama
    0.09
    奋斗
    0.09
     humanas
    0.09
     faithfully
    0.09
     intric
    0.09
     вза
    0.09
    揭
    0.09
    Activations Density 0.077%

    No Known Activations