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. 13026
    Prev
    Next
    INDEX
    Explanations

    process

    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
    .quit
    -0.08
     lento
    -0.08
     alapján
    -0.08
    .lazy
    -0.08
     Antiqu
    -0.07
     frutos
    -0.07
     upbeat
    -0.07
     lenta
    -0.07
     deciso
    -0.07
     და
    -0.07
    POSITIVE LOGITS
    вен
    0.08
     delivered
    0.08
    мы
    0.08
    保障
    0.08
    _marks
    0.07
    Deliver
    0.07
     órdenes
    0.07
    0.07
    保証
    0.07
     stamped
    0.07
    Activations Density 0.003%

    No Known Activations