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. 7-RESID-POST-AA
    6. 130962
    Prev
    Next
    INDEX
    Explanations

    namespace

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    、安全
    -0.07
    മ
    -0.07
    ाता
    -0.07
    ρύ
    -0.07
     Kentucky
    -0.07
     PAL
    -0.07
     respect
    -0.07
    ige
    -0.07
    Mw
    -0.07
    Choice
    -0.07
    POSITIVE LOGITS
    som
    0.08
     playoffs
    0.08
    以后
    0.08
     sperm
    0.08
     дальнейшем
    0.08
     heims
    0.07
    _parts
    0.07
     dunya
    0.07
     Moines
    0.07
     dood
    0.07
    Activations Density 0.001%

    No Known Activations