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. 11-RESID-POST-AA
    6. 75923
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
    낌
    -0.08
    %)
    -0.08
    NK
    -0.08
    )↵↵//
    -0.08
     soles
    -0.07
    …)
    -0.07
    NS
    -0.07
     Martí
    -0.07
     tokenizer
    -0.07
    새
    -0.07
    POSITIVE LOGITS
     wich
    0.09
    (that
    0.08
     seur
    0.08
     plugged
    0.08
     yht
    0.08
     Repairs
    0.08
     Ducks
    0.08
     episode
    0.07
     Aliment
    0.07
     ડિસ
    0.07
    Activations Density 0.073%

    No Known Activations