© 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. 65621
    Prev
    Next
    INDEX
    Explanations

    division remainders

    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
     확인
    -0.09
     Identity
    -0.08
     réun
    -0.08
    尼斯
    -0.07
     identity
    -0.07
     propuesta
    -0.07
     Theorie
    -0.07
     wedge
    -0.07
    motiv
    -0.07
    ians
    -0.07
    POSITIVE LOGITS
     decimals
    0.10
    Precision
    0.09
     expansions
    0.09
     decimal
    0.09
    逼
    0.09
     higher
    0.08
    _precision
    0.08
     iterative
    0.08
    Dividend
    0.08
     lamp
    0.08
    Activations Density 0.017%

    No Known Activations