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. 53929
    Prev
    Next
    INDEX
    Explanations

    bracket

    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
     doce
    -0.09
     izi
    -0.08
     Churchill
    -0.08
     Josh
    -0.08
    tube
    -0.07
     tui
    -0.07
     mgbe
    -0.07
     trekk
    -0.07
     seg
    -0.07
    🏼
    -0.07
    POSITIVE LOGITS
    Pa
    0.08
     Pa
    0.08
     Büro
    0.08
    .Visible
    0.08
    法人
    0.07
    .Var
    0.07
    .Reporting
    0.07
     cohesion
    0.07
    falto
    0.07
    办公室
    0.07
    Activations Density 0.028%

    No Known Activations