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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 67993
    Prev
    Next
    INDEX
    Explanations

    systems

    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
    。↵↵↵
    -0.09
    吻
    -0.09
    ↵		↵
    -0.09
    ).↵↵↵
    -0.09
    ">↵↵↵
    -0.08
     यही
    -0.08
    !↵↵↵
    -0.08
    >↵↵↵
    -0.08
    ,此
    -0.08
     */↵↵↵
    -0.07
    POSITIVE LOGITS
     або
    0.09
     немесе
    0.08
     või
    0.08
     hingegen
    0.08
     odnosno
    0.08
    거나
    0.08
     alebo
    0.08
     sogenannten
    0.08
     hoặc
    0.08
     અથવા
    0.07
    Activations Density 10.478%

    No Known Activations