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. 130829
    Prev
    Next
    INDEX
    Explanations

    say "the ending asti"

    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
    ոյ
    -0.09
    otoxic
    -0.08
    itness
    -0.08
    onal
    -0.08
    uelle
    -0.08
     Minist
    -0.08
    _endpoint
    -0.07
    ceptor
    -0.07
     þá
    -0.07
     ministros
    -0.07
    POSITIVE LOGITS
    ง่าย
    0.08
     ساده
    0.08
    LAN
    0.07
     社
    0.07
    :bg
    0.07
     gyr
    0.07
    asti
    0.07
    .Button
    0.07
    asto
    0.07
     menik
    0.07
    Activations Density 0.000%

    No Known Activations