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. 11-RESID-POST-AA
    6. 12699
    Prev
    Next
    INDEX
    Explanations

    Code mentioning Hilt

    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
     ഓ
    -0.08
     चुके
    -0.08
     �
    -0.07
     rehabilitation
    -0.07
    (audio
    -0.07
     ум
    -0.07
     ond
    -0.07
    tors
    -0.07
     rehabil
    -0.07
    音
    -0.07
    POSITIVE LOGITS
     welding
    0.08
     Nevada
    0.08
     Nat
    0.08
     Beverly
    0.08
     braz
    0.08
     ভিত
    0.08
    robi
    0.08
    כון
    0.07
     EI
    0.07
     Welding
    0.07
    Activations Density 0.000%

    No Known Activations