© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 54574
    Prev
    Next
    INDEX
    Explanations

    real

    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
     scanf
    -0.08
     whiten
    -0.08
    万人
    -0.08
    -hal
    -0.08
    white
    -0.07
     Force
    -0.07
     HAL
    -0.07
     arcs
    -0.07
     white
    -0.07
     FORCE
    -0.07
    POSITIVE LOGITS
    真钱
    0.14
    เงินจริง
    0.13
     echtes
    0.12
    投入
    0.12
     reales
    0.11
    投注
    0.11
     reais
    0.11
     деньги
    0.10
     dinero
    0.10
     реальные
    0.10
    Activations Density 0.013%

    No Known Activations