© 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. 44730
    Prev
    Next
    INDEX
    Explanations

    normal play games

    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
     Arsenal
    -0.08
     briefing
    -0.08
     arrogance
    -0.08
    29
    -0.07
    611
    -0.07
    197
    -0.07
    _SZ
    -0.07
    Station
    -0.07
     sleeves
    -0.07
     Mater
    -0.07
    POSITIVE LOGITS
     COMP
    0.09
     противоп
    0.08
    ditch
    0.08
    ท้าย
    0.08
     חוק
    0.08
     целью
    0.08
     პროცეს
    0.08
     კონტრ
    0.08
     geko
    0.08
     contraire
    0.08
    Activations Density 0.006%

    No Known Activations