© 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. 3-RESID-POST-AA
    11. 980
    Prev
    Next
    INDEX
    Explanations

    accord

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ли
    -0.08
     hyö
    -0.07
     scar
    -0.07
     امکانات
    -0.07
    weather
    -0.07
     Ki
    -0.07
     Aar
    -0.07
     平
    -0.07
     Meridian
    -0.07
     kios
    -0.07
    POSITIVE LOGITS
     misc
    0.10
     Naked
    0.08
     naked
    0.08
    depart
    0.07
    &O
    0.07
    ydın
    0.07
    Uno
    0.07
    รรณ
    0.07
    /'.
    0.07
     SCT
    0.07
    Activations Density 0.000%

    No Known Activations