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. 58493
    Prev
    Next
    INDEX
    Explanations

    tetrahedrons and EMDR

    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
     sugar
    -0.10
     сахар
    -0.08
    Sugar
    -0.08
     sweet
    -0.08
     pats
    -0.07
     السكر
    -0.07
     Sugar
    -0.07
     mosquito
    -0.07
     specific
    -0.07
     LAS
    -0.07
    POSITIVE LOGITS
     sentidos
    0.08
     Scaling
    0.08
     Ehren
    0.08
    ..<
    0.08
    angen
    0.08
    duced
    0.07
    atás
    0.07
     кеп
    0.07
     Arrangement
    0.07
    תח
    0.07
    Activations Density 0.000%

    No Known Activations