© 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. 51804
    Prev
    Next
    INDEX
    Explanations

    Chinese medicine prescriptions

    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
     tph
    -0.09
    pressive
    -0.08
     Yahoo
    -0.08
     والتح
    -0.08
     relaj
    -0.08
     Comedy
    -0.08
     mokhoa
    -0.08
     spambots
    -0.08
    ଟ
    -0.08
     trò
    -0.07
    POSITIVE LOGITS
     淫
    0.12
    黄片
    0.11
     人
    0.11
    川
    0.10
     atract
    0.10
    党
    0.10
    何
    0.10
    人
    0.10
     甘
    0.10
    柴
    0.09
    Activations Density 0.005%

    No Known Activations