© 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. 63245
    Prev
    Next
    INDEX
    Explanations

    0

    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
     intelligente
    -0.07
     Min
    -0.07
    onica
    -0.07
    МИ
    -0.07
    -song
    -0.07
    Evolution
    -0.07
    -job
    -0.07
     intelligent
    -0.07
    receive
    -0.07
    alaga
    -0.07
    POSITIVE LOGITS
    确定
    0.08
     aph
    0.08
     waiver
    0.08
    包装
    0.08
    无遮
    0.08
     xác
    0.08
     punct
    0.08
     tac
    0.08
    机制
    0.08
     AUS
    0.08
    Activations Density 0.000%

    No Known Activations