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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 47
    Prev
    Next
    INDEX
    Explanations

    mathematical operations

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sscanf
    -0.09
    訳
    -0.08
    .Shapes
    -0.08
     schu
    -0.08
     traduit
    -0.08
     встр
    -0.08
     protr
    -0.08
     cooked
    -0.08
     desayuno
    -0.08
     gegeten
    -0.08
    POSITIVE LOGITS
     cyc
    0.08
     exponent
    0.08
     modulo
    0.08
    Modulo
    0.08
     Establish
    0.08
    Lucas
    0.08
     शासन
    0.08
    cycles
    0.08
     establishing
    0.08
     regula
    0.08
    Activations Density 0.019%

    No Known Activations