© 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. 65608
    Prev
    Next
    INDEX
    Explanations

    erotic

    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
    હી
    -0.09
    shim
    -0.08
    ALLED
    -0.08
     testa
    -0.08
     כ
    -0.07
    เอง
    -0.07
     nada
    -0.07
    梁
    -0.07
     נ
    -0.07
    .viewport
    -0.07
    POSITIVE LOGITS
     lingerie
    0.10
    逐
    0.09
     soul
    0.08
    /night
    0.08
     Gras
    0.08
     музы
    0.08
     BAT
    0.08
    塑
    0.08
    атр
    0.08
     lays
    0.08
    Activations Density 0.003%

    No Known Activations