© 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. 51696
    Prev
    Next
    INDEX
    Explanations

    instructions

    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
     Would
    -0.11
     NONINFRINGEMENT
    -0.10
     南
    -0.10
     would
    -0.09
     ito
    -0.09
    ，会
    -0.09
     Specifically
    -0.09
     Please
    -0.09
     �
    -0.09
     Does
    -0.09
    POSITIVE LOGITS
    用
    0.21
    直接
    0.17
     用
    0.16
    通过
    0.15
    使用
    0.14
     dùng
    0.14
    改
    0.13
     rechtstreeks
    0.12
    ，用
    0.12
    创建
    0.12
    Activations Density 0.057%

    No Known Activations