© 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. 30277
    Prev
    Next
    INDEX
    Explanations

    do/perform

    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
    fel
    -0.09
    lated
    -0.08
    Fel
    -0.08
     childhood
    -0.08
     Mensch
    -0.08
     cilvē
    -0.08
    irse
    -0.08
    Pairs
    -0.08
     Needless
    -0.08
     празд
    -0.08
    POSITIVE LOGITS
     results
    0.09
     Ergebnisse
    0.08
     Results
    0.08
     interval
    0.08
     resultados
    0.08
     risultati
    0.08
     intervals
    0.08
     overcame
    0.07
     overcome
    0.07
     overcoming
    0.07
    Activations Density 0.002%

    No Known Activations