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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 99137
    Prev
    Next
    INDEX
    Explanations

    precise

    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
    ੋਂ
    -0.09
     Todd
    -0.08
    wohnung
    -0.08
    uhle
    -0.08
    覧
    -0.08
    .embedding
    -0.08
    496
    -0.08
     Afro
    -0.07
    omeza
    -0.07
     impresion
    -0.07
    POSITIVE LOGITS
    estens
    0.10
    மான
    0.08
     tuned
    0.08
     peri
    0.08
     موقع
    0.07
     constit
    0.07
     métier
    0.07
     ما
    0.07
    确
    0.07
     métiers
    0.07
    Activations Density 0.017%

    No Known Activations