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. 43187
    Prev
    Next
    INDEX
    Explanations

    sushi rolls, wrappers

    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
     Arbeitsplatz
    -0.09
     eingestellt
    -0.08
     perdas
    -0.08
     треб
    -0.08
     Cobra
    -0.08
     алт
    -0.08
     Erdog
    -0.08
     ceeb
    -0.08
    reibt
    -0.08
    шу
    -0.08
    POSITIVE LOGITS
     enclosing
    0.11
     envelopes
    0.08
    容
    0.08
     wrappers
    0.08
    iframe
    0.08
     encl
    0.08
    Outer
    0.08
    Hosting
    0.08
    outer
    0.07
     包
    0.07
    Activations Density 0.019%

    No Known Activations