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. 19101
    Prev
    Next
    INDEX
    Explanations

    code/language snippets

    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
     musamman
    -0.11
     acestea
    -0.10
     spécifiques
    -0.10
     זענען
    -0.10
     თითო
    -0.10
     xüsusi
    -0.10
     հատուկ
    -0.10
    .Usuario
    -0.10
     դրանք
    -0.10
     ყოვ
    -0.09
    POSITIVE LOGITS
    -if
    0.09
    now
    0.08
    -other
    0.08
    -from
    0.08
    owy
    0.08
    -time
    0.08
    way
    0.08
    oid
    0.08
    then
    0.08
    ometer
    0.07
    Activations Density 0.039%

    No Known Activations