© 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 EvalsExportsinterp-engineNEWAPI 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. 111519
    Prev
    Next
    INDEX
    Explanations

    about

    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
    عامل
    -0.09
     والث
    -0.08
     concernés
    -0.08
     الث
    -0.08
    .CO
    -0.08
     대상으로
    -0.08
     التعامل
    -0.07
    —including
    -0.07
     بب
    -0.07
    িতে
    -0.07
    POSITIVE LOGITS
     Manchester
    0.08
    舟
    0.08
    Manchester
    0.08
    Injected
    0.08
     Figur
    0.08
    educt
    0.08
    なく
    0.08
    orse
    0.07
     sate
    0.07
     quizá
    0.07
    Activations Density 0.002%

    No Known Activations