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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24628
    Prev
    Next
    INDEX
    Explanations

    corrected

    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
     expensive
    -0.08
    azane
    -0.08
    Hair
    -0.08
     ziliz
    -0.08
    ர்கள
    -0.08
     repayments
    -0.07
     wil
    -0.07
     зал
    -0.07
    性色
    -0.07
     blindly
    -0.07
    POSITIVE LOGITS
     संस्करण
    0.11
     version
    0.11
    版本
    0.11
     versão
    0.10
     версия
    0.10
     вариант
    0.09
     версии
    0.09
     versões
    0.09
     versione
    0.09
    版
    0.09
    Activations Density 0.013%

    No Known Activations