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. 130989
    Prev
    Next
    INDEX
    Explanations

    brands and products

    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
     salaries
    -0.09
     salários
    -0.08
     Stimmen
    -0.08
     organization's
    -0.08
    ον
    -0.08
     thermometer
    -0.08
     protiv
    -0.08
     steroid
    -0.08
    änä
    -0.08
    人的
    -0.08
    POSITIVE LOGITS
     tuin
    0.08
    yecto
    0.08
     הל
    0.08
     зроб
    0.07
     להז
    0.07
    itulo
    0.07
    Ey
    0.07
    aku
    0.07
    Diff
    0.07
     difusión
    0.07
    Activations Density 0.000%

    No Known Activations