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

    Neuronpedia

    APICircuit 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. 30586
    Prev
    Next
    INDEX
    Explanations

    ves

    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
     styr
    -0.08
     पो
    -0.08
     Gras
    -0.07
     disputed
    -0.07
    alis
    -0.07
    	info
    -0.07
     पहुँ
    -0.07
     चला
    -0.07
     останов
    -0.07
     अग्र
    -0.07
    POSITIVE LOGITS
     lookup
    0.10
    cdf
    0.09
    CDF
    0.09
     LUT
    0.09
     calibration
    0.09
     Lookup
    0.09
    lookup
    0.08
    .lookup
    0.08
     shade
    0.08
     personalizado
    0.08
    Activations Density 0.002%

    No Known Activations