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. 53846
    Prev
    Next
    INDEX
    Explanations

    is

    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
    馈
    -0.08
     decrement
    -0.08
    provided
    -0.08
    ayy
    -0.07
     Steuer
    -0.07
     mahimo
    -0.07
    prox
    -0.07
     soporte
    -0.07
     etiqueta
    -0.07
    оср
    -0.07
    POSITIVE LOGITS
     bustling
    0.10
     Buck
    0.08
     precar
    0.08
    ுது
    0.08
     يبدو
    0.08
     ينت
    0.08
     protagonist
    0.07
     Company
    0.07
     sleek
    0.07
    .ut
    0.07
    Activations Density 0.060%

    No Known Activations