© 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. 15-RESID-POST-AA
    11. 16580
    Prev
    Next
    INDEX
    Explanations

    do

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    பல
    -0.09
     가능
    -0.08
    ënd
    -0.08
     epä
    -0.08
     offensive
    -0.08
    ’ém
    -0.08
    Hoewel
    -0.08
     తర
    -0.08
     behoort
    -0.08
    专项
    -0.08
    POSITIVE LOGITS
     лишь
    0.15
     basta
    0.15
    ，只
    0.14
     suffit
    0.13
     بسيطة
    0.13
     lihtsalt
    0.13
     simply
    0.13
    即可
    0.13
     lediglich
    0.13
    简单
    0.13
    Activations Density 0.044%

    No Known Activations