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. 120387
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
    奉
    -0.08
    oused
    -0.08
     holl
    -0.08
    -0.08
    mon
    -0.07
    outer
    -0.07
    empt
    -0.07
    fire
    -0.07
    temps
    -0.07
    grav
    -0.07
    POSITIVE LOGITS
     reduct
    0.09
     NOV
    0.08
     ub
    0.07
     Gog
    0.07
     بر
    0.07
     POV
    0.07
     dbo
    0.07
    \Order
    0.07
     अश
    0.07
     challenger
    0.07
    Activations Density 0.375%

    No Known Activations