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. 15-RESID-POST-AA
    6. 32
    Prev
    Next
    INDEX
    Explanations

    brackets and braces

    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
     Loyola
    -0.07
    stream
    -0.07
    <|reserved_200016|>
    -0.07
     active
    -0.07
     theo
    -0.07
    (IO
    -0.07
     Lietuvos
    -0.07
     trực
    -0.07
    -0.07
     directly
    -0.07
    POSITIVE LOGITS
    "...
    0.10
    Something
    0.10
    XXXXX
    0.09
    ,...
    0.09
     irgendwann
    0.09
    (...)↵
    0.09
    /...
    0.09
    ...),
    0.09
     magiging
    0.08
    。。。
    0.08
    Activations Density 0.011%

    No Known Activations