© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 974
    Prev
    Next
    INDEX
    Explanations

    cryptography algorithms

    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
     theatre
    -0.09
     aroma
    -0.09
     appliances
    -0.09
     Orwell
    -0.09
     nutrient
    -0.08
     taste
    -0.08
    taste
    -0.08
     punctuation
    -0.08
    (xhr
    -0.08
     чувство
    -0.08
    POSITIVE LOGITS
     Ethereum
    0.10
    Bitcoin
    0.09
     Coinbase
    0.09
     elegant
    0.09
     verilen
    0.09
     ellipt
    0.09
    自拍
    0.09
     Elegant
    0.09
    Ethereum
    0.08
     Bitcoin
    0.08
    Activations Density 0.003%

    No Known Activations