Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43957
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     unbe
    -0.09
    porter
    -0.08
     полноцен
    -0.08
    ión
    -0.08
    ctrl
    -0.08
     shareholder
    -0.08
    共享
    -0.07
     preached
    -0.07
     espectacular
    -0.07
     trolling
    -0.07
    POSITIVE LOGITS
     reasoning
    0.09
     computations
    0.08
     계산
    0.08
     calculations
    0.08
     
    0.08
     Kem
    0.08
     Calculation
    0.08
    步骤
    0.08
     Step
    0.08
    ‐
    0.08
    Activations Density 0.033%

    No Known Activations