© 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 EvalsExportsAPI 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. 64196
    Prev
    Next
    INDEX
    Explanations

    complementary

    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
    DDL
    -0.09
     understandably
    -0.08
     sanya
    -0.08
     години
    -0.08
     сала
    -0.08
     amusing
    -0.08
     concaten
    -0.08
     precious
    -0.07
    ggreg
    -0.07
     гады
    -0.07
    POSITIVE LOGITS
     oposição
    0.09
     विरोध
    0.09
     opposite
    0.09
     oposición
    0.09
     विप
    0.09
     complementar
    0.09
     According
    0.08
     complement
    0.08
     Complement
    0.08
     oppos
    0.08
    Activations Density 0.005%

    No Known Activations