© 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. 54687
    Prev
    Next
    INDEX
    Explanations

    past

    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
     المصنعة
    -0.08
     Afgan
    -0.08
    radi
    -0.08
    atira
    -0.08
     sade
    -0.08
    stelling
    -0.08
     tier
    -0.08
     plena
    -0.08
    ाठम
    -0.08
    Alphabet
    -0.07
    POSITIVE LOGITS
     గత
    0.08
     사건
    0.08
     geçmiş
    0.07
     liter
    0.07
     incorporates
    0.07
    지난
    0.07
     helps
    0.07
    yectos
    0.07
    事务
    0.07
     گذشته
    0.07
    Activations Density 0.000%

    No Known Activations