Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77226
    Prev
    Next
    INDEX
    Explanations

    mathematical sets and closures

    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
     horseback
    -0.08
     кус
    -0.08
    celer
    -0.08
     widths
    -0.07
     pyt
    -0.07
     цвет
    -0.07
     हाल
    -0.07
     bevestigd
    -0.07
     pug
    -0.07
     mão
    -0.07
    POSITIVE LOGITS
     દી
    0.08
    hoo
    0.08
    887
    0.08
    ilmiş
    0.08
     acúst
    0.08
     encompassing
    0.07
    思想
    0.07
    究
    0.07
    ifikasi
    0.07
     Concepts
    0.07
    Activations Density 0.003%

    No Known Activations