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. 19189
    Prev
    Next
    INDEX
    Explanations

    to

    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
    .↵↵
    -0.10
    ,
    -0.09
    ÷
    -0.08
    —and
    -0.08
    .
    -0.08
    .Graph
    -0.08
    ');↵↵
    -0.07
    ',
    -0.07
    gleichen
    -0.07
    _Click
    -0.07
    POSITIVE LOGITS
     faciliter
    0.09
     farine
    0.09
     պատմ
    0.09
     hoʻ
    0.08
     الحركة
    0.08
     suf
    0.08
     Ljubl
    0.08
     insinu
    0.08
     erleich
    0.08
    能提现
    0.08
    Activations Density 0.001%

    No Known Activations