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

    Neuronpedia

    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. 99785
    Prev
    Next
    INDEX
    Explanations

    test question generation

    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
     limitless
    -0.08
     ❤️
    -0.08
     Awe
    -0.08
     préserver
    -0.07
     ales
    -0.07
     Truly
    -0.07
     Weed
    -0.07
     pest
    -0.07
    whel
    -0.07
     náv
    -0.07
    POSITIVE LOGITS
     প্রশ্ন
    0.09
     interpretação
    0.09
     Suppose
    0.08
     গণ
    0.08
     وتص
    0.08
     السؤال
    0.08
    Pregunta
    0.08
     মৌ
    0.08
    询
    0.08
    (correct
    0.08
    Activations Density 0.023%

    No Known Activations