© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 69050
    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
     الالت
    -0.09
    edas
    -0.08
    íu
    -0.07
    ेस
    -0.07
     تج
    -0.07
     concatenate
    -0.07
     hab
    -0.07
    រ
    -0.07
    iju
    -0.07
    iu
    -0.07
    POSITIVE LOGITS
     Shop
    0.08
     ആണ്
    0.08
     satisfies
    0.08
    ショップ
    0.08
     tertentu
    0.08
     gives
    0.08
     shops
    0.08
    trash
    0.08
     something
    0.08
    okwu
    0.08
    Activations Density 0.096%

    No Known Activations