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. 11992
    Prev
    Next
    INDEX
    Explanations

    carbon dioxide

    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
     Shrine
    -0.08
     signature
    -0.08
     blood
    -0.07
    umia
    -0.07
     ایمان
    -0.07
     חל
    -0.07
     iets
    -0.07
     occupational
    -0.07
    -0.07
     delir
    -0.07
    POSITIVE LOGITS
    pon
    0.09
     vårt
    0.08
     Pron
    0.08
     Gregory
    0.08
    .template
    0.08
    Stephen
    0.08
    ̂
    0.08
    opoly
    0.08
    Pron
    0.08
    Bak
    0.08
    Activations Density 0.003%

    No Known Activations