© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 47736
    Prev
    Next
    INDEX
    Explanations

    net

    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
     Stud
    -0.07
     fw
    -0.07
     the
    -0.07
     a
    -0.07
     Robertson
    -0.07
    uton
    -0.07
    Stud
    -0.07
     Adventure
    -0.07
     Able
    -0.07
     Astr
    -0.07
    POSITIVE LOGITS
    Complement
    0.12
     Complement
    0.12
     complemento
    0.11
     complementar
    0.11
     complementary
    0.11
     complements
    0.11
     Ergän
    0.11
     ergän
    0.10
     supplementation
    0.10
     complement
    0.10
    Activations Density 0.112%

    No Known Activations