Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12492
    Prev
    Next
    INDEX
    Explanations

    infinit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (mx
    -0.09
     Prote
    -0.08
     Denis
    -0.08
     Wynn
    -0.07
     Hathaway
    -0.07
     Essex
    -0.07
     estr
    -0.07
     بو
    -0.07
    (dw
    -0.07
    PRISE
    -0.07
    POSITIVE LOGITS
     bich
    0.09
     Vic
    0.08
     Cra
    0.07
     tý
    0.07
     бағы
    0.07
     furn
    0.07
     ​​
    0.07
    olak
    0.07
    Vic
    0.07
     الفرق
    0.07
    Activations Density 0.002%

    No Known Activations