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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 76544
    Prev
    Next
    INDEX
    Explanations

    fluffy

    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
    谋
    -0.09
     물론
    -0.08
    식을
    -0.08
     impr
    -0.08
     queira
    -0.08
     обратно
    -0.08
     сторону
    -0.08
    lossen
    -0.08
    _VOID
    -0.08
     Garg
    -0.08
    POSITIVE LOGITS
    -to
    0.08
    宝宝
    0.08
     animals
    0.07
     ഉട
    0.07
     adjectives
    0.07
     Taylor
    0.07
     monkeys
    0.07
     nursery
    0.07
    Taylor
    0.07
     Button
    0.07
    Activations Density 0.003%

    No Known Activations