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. 30623
    Prev
    Next
    INDEX
    Explanations

    arm

    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
    Sono
    -0.11
    xer
    -0.09
     Sono
    -0.09
     salvo
    -0.08
    лл
    -0.08
     Cer
    -0.08
    Factor
    -0.08
     spoiler
    -0.08
    Ł
    -0.08
    Cancelable
    -0.07
    POSITIVE LOGITS
     cabinets
    0.10
     шкаф
    0.10
     sofas
    0.09
     мебель
    0.09
     мебели
    0.09
     �
    0.09
     furniture
    0.09
     Cabinets
    0.08
     upholstered
    0.08
    家具
    0.08
    Activations Density 0.006%

    No Known Activations