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. 53948
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations

    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
     girlfriend
    -0.08
     dith
    -0.08
     увелич
    -0.08
     congrat
    -0.08
     Assault
    -0.08
     akkoord
    -0.08
    领取
    -0.08
     forgiving
    -0.08
    阵
    -0.08
     discretion
    -0.08
    POSITIVE LOGITS
     phenomena
    0.13
     uncover
    0.11
    patterns
    0.10
     patterns
    0.10
     mysteries
    0.10
     interplay
    0.10
    Patterns
    0.10
    _patterns
    0.10
     Patterns
    0.09
    揭
    0.09
    Activations Density 0.055%

    No Known Activations