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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19069
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     համապատասխան
    -0.09
     ارد
    -0.09
    GES
    -0.09
     ՝
    -0.09
     ে
    -0.09
     	i
    -0.09
     նկատ
    -0.09
     ել
    -0.09
     joku
    -0.09
     Sesame
    -0.09
    POSITIVE LOGITS
    Ⅱ
    0.14
    1
    0.14
    200
    0.14
    60
    0.13
    24
    0.13
    12
    0.13
    2
    0.13
    180
    0.13
    10
    0.13
    90
    0.13
    Activations Density 0.073%

    No Known Activations