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. 98056
    Prev
    Next
    INDEX
    Explanations

    .read

    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
    :size
    -0.08
    ੰਦ
    -0.08
    -two
    -0.08
    :UIControl
    -0.08
    ➡
    -0.07
    byen
    -0.07
    @One
    -0.07
    <size
    -0.07
     aand
    -0.07
     playlists
    -0.07
    POSITIVE LOGITS
    _sql
    0.16
    _csv
    0.16
    _excel
    0.14
    _html
    0.13
    _clip
    0.13
    _json
    0.12
    _par
    0.12
    _pickle
    0.12
    _fe
    0.12
    Sql
    0.11
    Activations Density 0.001%

    No Known Activations