© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 22492
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ABET
    -0.08
     encrypt
    -0.08
    IFICATION
    -0.07
    ITERAL
    -0.07
    ADDING
    -0.07
    tid
    -0.07
     uploading
    -0.07
    发送
    -0.07
    日电
    -0.07
    在线播放
    -0.07
    POSITIVE LOGITS
    isserie
    0.10
     onions
    0.10
     vegetables
    0.10
    ing
    0.10
     овощ
    0.10
     کردن
    0.10
     browned
    0.10
     veggies
    0.10
    ंगी
    0.10
     légumes
    0.10
    Activations Density 0.003%

    No Known Activations