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. 56012
    Prev
    Next
    INDEX
    Explanations

    bola

    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
     equiv
    -0.08
     ballots
    -0.08
    asser
    -0.08
     laiss
    -0.08
    akin
    -0.07
     vacation
    -0.07
    emand
    -0.07
    ifel
    -0.07
    ivered
    -0.07
     joking
    -0.07
    POSITIVE LOGITS
     الشكل
    0.09
     الخط
    0.09
    .CENTER
    0.08
     moons
    0.08
    [['
    0.08
     �
    0.08
     frac
    0.08
     Wen
    0.07
     Barnes
    0.07
    事实
    0.07
    Activations Density 0.006%

    No Known Activations