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. 53015
    Prev
    Next
    INDEX
    Explanations

    Cooking instructions

    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
     cones
    -0.08
    733
    -0.08
     cone
    -0.08
     अभिय
    -0.07
    -0.07
    /MPL
    -0.07
    uo
    -0.07
     electrode
    -0.07
     Cone
    -0.07
    -0.07
    POSITIVE LOGITS
     удел
    0.08
     lapho
    0.08
     Nesta
    0.08
    designation
    0.08
     სანამ
    0.08
     იგი
    0.08
     동안
    0.07
     loko
    0.07
     مرحله
    0.07
    전히
    0.07
    Activations Density 0.008%

    No Known Activations