© 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. 64975
    Prev
    Next
    INDEX
    Explanations

    points

    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
     товара
    -0.08
    293
    -0.08
    商品の
    -0.07
     dépasse
    -0.07
     organ
    -0.07
    പ്പെടുത്തി
    -0.07
     gaining
    -0.07
    Kas
    -0.07
     propagate
    -0.07
     maiden
    -0.06
    POSITIVE LOGITS
    (Size
    0.09
    (This
    0.08
     sprinkled
    0.08
     fle
    0.07
    oths
    0.07
    flakes
    0.07
    spers
    0.07
     Centr
    0.07
    estable
    0.07
     ఒక
    0.07
    Activations Density 0.015%

    No Known Activations