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. 76069
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
     angene
    -0.08
     NOK
    -0.08
     ashes
    -0.08
     sáng
    -0.08
     alsof
    -0.08
     skjer
    -0.07
    -0.07
    Screens
    -0.07
     erfolgt
    -0.07
     smoke
    -0.07
    POSITIVE LOGITS
     theorem
    0.10
    公式
    0.10
     fórmula
    0.09
     formulas
    0.09
     formule
    0.09
     recalled
    0.09
     trusty
    0.08
     воспользоваться
    0.08
     machinery
    0.08
     formula
    0.08
    Activations Density 0.060%

    No Known Activations