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. 88286
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     Roberts
    -0.09
     moot
    -0.08
     അട
    -0.08
    /business
    -0.08
     Caso
    -0.07
     emancip
    -0.07
     Clerk
    -0.07
     perp
    -0.07
     accidental
    -0.07
     Stranger
    -0.07
    POSITIVE LOGITS
     تست
    0.08
    £
    0.08
    ఉ
    0.08
     Geld
    0.08
     żad
    0.07
     مدت
    0.07
    JSON
    0.07
     meis
    0.07
    ordinal
    0.07
    ...
    0.07
    Activations Density 0.008%

    No Known Activations