© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44754
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     cient
    -0.08
    ാപ
    -0.08
    科学
    -0.08
    参数
    -0.08
     वन
    -0.08
     biome
    -0.08
    甚至
    -0.07
    _iterations
    -0.07
    定位
    -0.07
    Iterations
    -0.07
    POSITIVE LOGITS
     Receipt
    0.10
     deduct
    0.10
    receipt
    0.10
     receipt
    0.10
     Transaction
    0.09
     transactions
    0.09
     transaksi
    0.09
     escrow
    0.09
     Received
    0.09
    Receipt
    0.09
    Activations Density 0.004%

    No Known Activations