© 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 EvalsExportsinterp-engineNEWAPI 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. 110870
    Prev
    Next
    INDEX
    Explanations

    math competition 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
     रखा
    -0.08
     온
    -0.08
     نمای
    -0.08
     поддерж
    -0.08
     persona
    -0.08
    へ
    -0.07
     μπορεί
    -0.07
    _tid
    -0.07
     demanding
    -0.07
     personas
    -0.07
    POSITIVE LOGITS
    -letter
    0.09
    Morgan
    0.08
    Contest
    0.08
    Letter
    0.08
     Morgan
    0.08
     Exhibit
    0.08
    Headline
    0.08
    Earn
    0.07
    Letters
    0.07
     AMC
    0.07
    Activations Density 0.004%

    No Known Activations