© 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. 7713
    Prev
    Next
    INDEX
    Explanations

    guilty

    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
     Catering
    -0.09
     pumping
    -0.08
     watercolor
    -0.08
     Mus
    -0.08
     Ches
    -0.08
    .proto
    -0.07
    coop
    -0.07
    (proto
    -0.07
     Hind
    -0.07
     ty
    -0.07
    POSITIVE LOGITS
     अपराध
    0.13
    罪
    0.13
    犯罪
    0.13
     crimin
    0.12
     guilt
    0.11
     преступ
    0.11
     കുറ്റ
    0.11
     wrongdoing
    0.11
    Violation
    0.11
     crimes
    0.11
    Activations Density 0.045%

    No Known Activations