© 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. 23-RESID-POST-AA
    11. 47634
    Prev
    Next
    INDEX
    Explanations

    Command & Conquer games

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     પ્રવાસ
    -0.09
     ફોટ
    -0.09
     புக
    -0.08
     மருத்த
    -0.08
     vélo
    -0.08
     ડ્ર
    -0.08
     хирург
    -0.08
     драй
    -0.08
     surgical
    -0.08
    гот
    -0.08
    POSITIVE LOGITS
     Echt
    0.09
    实时
    0.09
     realtime
    0.09
     Yuri
    0.09
     Command
    0.08
    即时
    0.08
     coal
    0.08
    AI
    0.08
     Coal
    0.08
    Coal
    0.08
    Activations Density 0.002%

    No Known Activations