Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 58290
    Prev
    Next
    INDEX
    Explanations

    Card counting

    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
     bump
    -0.08
    east
    -0.07
    sir
    -0.07
     topping
    -0.07
     pathway
    -0.07
    Virgin
    -0.07
    老
    -0.07
     sabab
    -0.07
     Euro
    -0.07
     Sequ
    -0.07
    POSITIVE LOGITS
     مراق
    0.09
     Enables
    0.09
     حساب
    0.08
     thc
    0.07
    ▒
    0.07
     ther
    0.07
    راق
    0.07
     Neuk
    0.07
     Calvin
    0.07
     disf
    0.07
    Activations Density 0.003%

    No Known Activations