© 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 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. 69874
    Prev
    Next
    INDEX
    Explanations

    DISM image repair commands

    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
    棋
    -0.08
    冲
    -0.08
     stereotyp
    -0.08
     percussion
    -0.08
    比赛
    -0.08
     stereotypes
    -0.07
    �
    -0.07
     scher
    -0.07
     stereotype
    -0.07
    催
    -0.07
    POSITIVE LOGITS
    náv
    0.09
     �
    0.08
     unterstützt
    0.08
     destek
    0.08
    enuous
    0.08
     동일
    0.08
     문의
    0.08
    -maint
    0.08
    очная
    0.08
    Mos
    0.08
    Activations Density 0.001%

    No Known Activations