© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 52286
    Prev
    Next
    INDEX
    Explanations

    multilingual

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    égr
    -0.09
    ீ
    -0.08
    ிட்ட
    -0.08
     reserv
    -0.07
    \App
    -0.07
     suport
    -0.07
    ிட
    -0.07
     tread
    -0.07
    િટ
    -0.07
    面积
    -0.07
    POSITIVE LOGITS
     actualizado
    0.08
    更新
    0.08
    vient
    0.08
     redo
    0.08
     업데이트
    0.08
     confirmé
    0.08
     Викип
    0.08
    老虎机
    0.08
     WIB
    0.08
     wiki
    0.07
    Activations Density 0.000%

    No Known Activations