© 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. 70389
    Prev
    Next
    INDEX
    Explanations

    otted

    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
     bolest
    -0.09
    dated
    -0.08
     amzer
    -0.08
     advantages
    -0.08
    եզ
    -0.08
    ifacts
    -0.08
     dialect
    -0.08
    ("%.
    -0.08
    azzjonijiet
    -0.08
     المض
    -0.08
    POSITIVE LOGITS
     Grün
    0.08
     Officer
    0.08
     greenery
    0.08
     Kong
    0.08
     mantienen
    0.07
     mantiene
    0.07
    咪
    0.07
     foliage
    0.07
     বজ
    0.07
    主管
    0.07
    Activations Density 0.022%

    No Known Activations