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. 43310
    Prev
    Next
    INDEX
    Explanations

    rhythm

    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
    تە
    -0.09
    OPTION
    -0.08
     البشر
    -0.08
    流程
    -0.08
     החיים
    -0.08
    .batch
    -0.07
     belajar
    -0.07
    ability
    -0.07
     toka
    -0.07
     flow
    -0.07
    POSITIVE LOGITS
    0.08
    ondo
    0.08
     अग
    0.08
     coloration
    0.08
    ाना
    0.07
    ollider
    0.07
     Colonel
    0.07
     embroidery
    0.07
     stuffing
    0.07
     Josef
    0.07
    Activations Density 0.003%

    No Known Activations