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. 90173
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     substantial
    -0.08
     verp
    -0.08
     umbrella
    -0.07
     extensive
    -0.07
    ाऱ्या
    -0.07
     voertu
    -0.07
     requisite
    -0.07
    चर
    -0.07
     Outdoor
    -0.07
     piis
    -0.07
    POSITIVE LOGITS
    ,因为
    0.10
     👉
    0.09
    ,当
    0.09
    Truthy
    0.09
     النات
    0.08
     получится
    0.08
     Fahrenheit
    0.08
    ,那么
    0.08
     результата
    0.08
    结果
    0.08
    Activations Density 0.091%

    No Known Activations