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. 19106
    Prev
    Next
    INDEX
    Explanations

    (

    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
     કમ
    -0.09
     Cond
    -0.08
    нік
    -0.08
     Wilderness
    -0.08
     కమ
    -0.07
    -five
    -0.07
     GPIO
    -0.07
     ouvi
    -0.07
     Roche
    -0.07
     rowspan
    -0.07
    POSITIVE LOGITS
    !(
    0.09
    addition
    0.09
    μα
    0.08
    lexer
    0.08
    adding
    0.08
    maß
    0.08
     любое
    0.08
    manager
    0.08
    ?(
    0.08
    arlı
    0.08
    Activations Density 0.013%

    No Known Activations