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. 11903
    Prev
    Next
    INDEX
    Explanations

    Uses emojis

    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
     someday
    -0.08
    aris
    -0.08
    시험
    -0.08
     결국
    -0.08
     getest
    -0.08
     ಪರೀಕ್ಷ
    -0.08
     Weiterbildung
    -0.08
    TLS
    -0.08
    -0.07
     Nissan
    -0.07
    POSITIVE LOGITS
     decorate
    0.11
     accents
    0.11
     punctuation
    0.11
     alegre
    0.11
     decorative
    0.11
     playful
    0.10
     embell
    0.10
     Decorative
    0.10
     cheerful
    0.10
     sprinkle
    0.10
    Activations Density 0.006%

    No Known Activations