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. 11-RESID-POST-AA
    6. 60788
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rol
    -0.08
     siège
    -0.08
    -ż
    -0.08
     علی
    -0.07
     Rico
    -0.07
     Accordingly
    -0.07
    `}>↵
    -0.07
     ----------------------------------------------------------------
    -0.07
     нал
    -0.07
     EO
    -0.07
    POSITIVE LOGITS
    tab
    0.09
     completos
    0.08
    .ct
    0.08
    kir
    0.07
     manipulating
    0.07
    hta
    0.07
    gl
    0.07
    ણા
    0.07
     tab
    0.07
     archaeological
    0.07
    Activations Density 0.125%

    No Known Activations