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. 75977
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Calculator
    -0.08
     rowing
    -0.08
    Calculator
    -0.08
     gymnast
    -0.08
     virg
    -0.08
     stationery
    -0.07
     vomiting
    -0.07
     lemonade
    -0.07
     একটু
    -0.07
     Dusche
    -0.07
    POSITIVE LOGITS
     schaffen
    0.09
    新时代
    0.08
     pioneered
    0.08
     innov
    0.08
    innov
    0.08
     enables
    0.08
     Tief
    0.08
     Jiang
    0.08
    采用
    0.08
     enjeux
    0.08
    Activations Density 0.012%

    No Known Activations