© 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. 26124
    Prev
    Next
    INDEX
    Explanations

    arctan with quadrant adjustments

    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
     wagering
    -0.08
     thrive
    -0.08
    娃
    -0.08
    -dev
    -0.08
    .db
    -0.07
     强
    -0.07
     breathing
    -0.07
     Spons
    -0.07
    Roboto
    -0.07
    _FIXED
    -0.07
    POSITIVE LOGITS
     quadrant
    0.13
     atan
    0.10
     situe
    0.10
     անկ
    0.09
    .atan
    0.09
     ხარისხ
    0.09
     սխ
    0.09
     სამხედრო
    0.09
    ourn
    0.09
     กม
    0.09
    Activations Density 0.016%

    No Known Activations