© 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. 23-RESID-POST-AA
    11. 50335
    Prev
    Next
    INDEX
    Explanations

    深

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deepen
    -0.09
     deeper
    -0.09
    深
    -0.09
     depths
    -0.09
     deep
    -0.09
     aprofund
    -0.09
     approfond
    -0.08
    Deep
    -0.08
     deeply
    -0.08
    深入
    -0.08
    POSITIVE LOGITS
    度
    0.11
     learning
    0.11
     lær
    0.10
     러
    0.10
    SUM
    0.10
     뉴
    0.10
    _learning
    0.10
     belief
    0.09
     Learning
    0.09
     reinforcement
    0.09
    Activations Density 0.002%

    No Known Activations