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. 79
    Prev
    Next
    INDEX
    Explanations

    Credit card digits

    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
     surveyed
    -0.09
     мульт
    -0.09
     survey
    -0.09
     ко
    -0.08
     yapan
    -0.08
    ENCY
    -0.08
     reunión
    -0.08
     surveying
    -0.08
    图库
    -0.08
    .collections
    -0.07
    POSITIVE LOGITS
     digits
    0.11
     masked
    0.11
    digits
    0.11
    号码
    0.11
     panjang
    0.11
     shortened
    0.10
    尾
    0.10
     checksum
    0.10
     Visa
    0.10
     নিরাপ
    0.10
    Activations Density 0.005%

    No Known Activations