© 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. 1141
    Prev
    Next
    INDEX
    Explanations

    Chinese word for "strong"

    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
    佩
    -0.09
     Terap
    -0.08
    .Bind
    -0.08
    zem
    -0.08
    曝
    -0.07
     packages
    -0.07
     обязатель
    -0.07
     Bedien
    -0.07
     बाँ
    -0.07
     बां
    -0.07
    POSITIVE LOGITS
     greatness
    0.11
     proud
    0.10
     nation
    0.10
    壮
    0.10
    实力
    0.10
     pride
    0.10
    -strength
    0.09
     proudly
    0.09
     stature
    0.09
     stolz
    0.09
    Activations Density 0.013%

    No Known Activations