© 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. 51580
    Prev
    Next
    INDEX
    Explanations

    learning and activities

    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
    用于
    -0.10
    出售
    -0.09
    하여
    -0.09
     settlers
    -0.09
    용
    -0.09
    用
    -0.08
    Agregar
    -0.08
     用
    -0.08
    Sett
    -0.08
    終了
    -0.08
    POSITIVE LOGITS
    钱怎么
    0.17
    东西
    0.13
    钱
    0.13
    饭
    0.13
     chuyện
    0.11
     चीज
    0.11
    事情
    0.11
    假吗
    0.11
     things
    0.11
     tiền
    0.11
    Activations Density 0.066%

    No Known Activations