© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113588
    Prev
    Next
    INDEX
    Explanations

    math problems with constraints

    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
    ادت
    -0.10
     Mary
    -0.08
    _BAD
    -0.07
    قسم
    -0.07
    ","\
    -0.07
     merge
    -0.07
     birleş
    -0.07
     holiness
    -0.07
     Sér
    -0.07
     (\
    -0.07
    POSITIVE LOGITS
     paggamit
    0.10
     използ
    0.10
     utilização
    0.10
     ఉపయోగ
    0.09
    发挥
    0.09
     использования
    0.09
     χρήση
    0.09
     사용하는
    0.09
     사용할
    0.09
     uporabo
    0.09
    Activations Density 0.047%

    No Known Activations