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. 12133
    Prev
    Next
    INDEX
    Explanations

    [

    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
     estacion
    -0.08
     इस्त
    -0.08
     UF
    -0.07
     techo
    -0.07
    \f
    -0.07
     Station
    -0.07
    \e
    -0.07
     iron
    -0.07
     cradle
    -0.07
     algun
    -0.07
    POSITIVE LOGITS
    _detect
    0.09
     പുല
    0.08
     Από
    0.08
     ngaw
    0.08
    獸
    0.08
    ثار
    0.08
    _tiles
    0.08
     apparition
    0.08
    639
    0.07
    ilia
    0.07
    Activations Density 0.003%

    No Known Activations