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. 9149
    Prev
    Next
    INDEX
    Explanations

    Javascript keywords

    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
    -pay
    -0.08
     起
    -0.08
    'avons
    -0.08
    onsum
    -0.08
    acar
    -0.08
     Apost
    -0.07
    ਾਸ
    -0.07
    قطع
    -0.07
     weil
    -0.07
    ált
    -0.07
    POSITIVE LOGITS
     slows
    0.08
     CK
    0.07
    ↵      ↵
    0.07
     cud
    0.07
     bem
    0.07
     Auth
    0.07
     Tage
    0.07
     FE
    0.07
     bout
    0.07
     cadastr
    0.07
    Activations Density 0.004%

    No Known Activations