© 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. 69370
    Prev
    Next
    INDEX
    Explanations

    computer programming

    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
     Payments
    -0.09
     payouts
    -0.09
    Payments
    -0.08
    .download
    -0.08
    的彩票
    -0.08
    download
    -0.08
     выплаты
    -0.07
     bowl
    -0.07
    ikisha
    -0.07
    ọpụta
    -0.07
    POSITIVE LOGITS
     principles
    0.11
     concepts
    0.09
     cohesion
    0.08
     princípios
    0.08
    模式
    0.08
     restructuring
    0.08
     prinsip
    0.08
     ввод
    0.08
     conceitos
    0.08
     efficacement
    0.08
    Activations Density 0.005%

    No Known Activations