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. 65184
    Prev
    Next
    INDEX
    Explanations

    .sql and .table

    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
     electrode
    -0.08
     ROCK
    -0.07
     remote
    -0.07
     unfolded
    -0.07
    gift
    -0.07
     xog
    -0.07
    remote
    -0.07
     Cub
    -0.07
     Cuban
    -0.07
     flea
    -0.07
    POSITIVE LOGITS
     النساء
    0.08
     kvinner
    0.08
     따르면
    0.08
    .window
    0.08
     chase
    0.08
    专
    0.07
    pertino
    0.07
     acad
    0.07
     المرأة
    0.07
     ਹਨ
    0.07
    Activations Density 0.001%

    No Known Activations