© 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. 23-RESID-POST-AA
    11. 48094
    Prev
    Next
    INDEX
    Explanations

    ingredients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conferences
    -0.09
     महामारी
    -0.08
     conferences
    -0.08
    新闻网
    -0.08
     tồn
    -0.08
     باوجود
    -0.08
     tablo
    -0.08
     epidem
    -0.08
    Queryable
    -0.08
    xmlns
    -0.08
    POSITIVE LOGITS
     ингреди
    0.21
     toppings
    0.18
     Zutaten
    0.17
     ingredients
    0.17
     ingredientes
    0.16
     marinade
    0.16
     ingrediënten
    0.16
     sauce
    0.15
     ingred
    0.15
    Ingredients
    0.14
    Activations Density 0.057%

    No Known Activations