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. 23-RESID-POST-AA
    6. 98054
    Prev
    Next
    INDEX
    Explanations

    M

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    айн
    -0.10
     감독
    -0.09
     하지
    -0.08
     interesses
    -0.08
     Заб
    -0.08
     हित
    -0.08
     τά
    -0.08
    äten
    -0.08
     mettre
    -0.08
    vloer
    -0.08
    POSITIVE LOGITS
    ush
    0.10
    iso
    0.09
    ذا
    0.09
     carrot
    0.09
    ango
    0.08
    ANGO
    0.08
    oric
    0.08
    ushy
    0.08
    eliac
    0.08
    irin
    0.08
    Activations Density 0.019%

    No Known Activations