© 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. 70457
    Prev
    Next
    INDEX
    Explanations

    graphene

    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
    ונג
    -0.09
    וע
    -0.08
     afge
    -0.08
     vog
    -0.07
     mettent
    -0.07
     mest
    -0.07
     aten
    -0.07
     fordi
    -0.07
     showed
    -0.07
     geometr
    -0.07
    POSITIVE LOGITS
     constitucional
    0.09
     Jér
    0.08
     Huffington
    0.08
     splitting
    0.08
     الحقوق
    0.08
    初始化
    0.08
     Hollande
    0.08
    法
    0.08
    司法
    0.08
     BUR
    0.07
    Activations Density 0.002%

    No Known Activations