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. 11-RESID-POST-AA
    6. 120342
    Prev
    Next
    INDEX
    Explanations

    decimals

    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
     candid
    -0.08
     raven
    -0.07
     구축
    -0.07
    stdb
    -0.07
     agh
    -0.07
     тим
    -0.07
    тии
    -0.07
    .emit
    -0.07
     buff
    -0.07
     раст
    -0.07
    POSITIVE LOGITS
     Widow
    0.08
     (_)
    0.07
     Kisi
    0.07
     sencilla
    0.07
     patios
    0.07
     kokoa
    0.07
     Whereas
    0.07
     jm
    0.07
    ยม
    0.07
     widow
    0.07
    Activations Density 0.021%

    No Known Activations