© 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. 68490
    Prev
    Next
    INDEX
    Explanations

    to

    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
     운영
    -0.09
     추천
    -0.08
    "Our
    -0.08
     우리
    -0.08
     suddenly
    -0.08
    اضر
    -0.08
    곳
    -0.08
     특히
    -0.08
    ================================================================
    -0.08
     ہمارے
    -0.08
    POSITIVE LOGITS
     reasoning
    0.10
     ability
    0.10
     skills
    0.09
     instincts
    0.09
     noticing
    0.09
     guess
    0.09
     deduction
    0.09
     quickly
    0.09
     easy
    0.09
     ingenuity
    0.08
    Activations Density 0.046%

    No Known Activations