© 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. 110240
    Prev
    Next
    INDEX
    Explanations

    Non-English language fragments

    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
     داشتن
    -0.08
     himself
    -0.08
    ei
    -0.08
    ে
    -0.08
    ๆ
    -0.08
     selves
    -0.07
     LA
    -0.07
     überras
    -0.07
     Zhu
    -0.07
    -0.07
    POSITIVE LOGITS
     başlan
    0.11
     gekeken
    0.10
     kullanıl
    0.10
     yapıl
    0.09
     الموض
    0.08
     dech
    0.08
     festgestellt
    0.08
     мной
    0.08
    ukke
    0.08
     dilakukan
    0.08
    Activations Density 0.366%
    No Known Activations