© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 52238
    Prev
    Next
    INDEX
    Explanations

    I or you

    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
     velmi
    -0.12
     todella
    -0.12
     väldigt
    -0.12
     veoma
    -0.12
     Things
    -0.11
     goodies
    -0.11
     iyong
    -0.11
     شيئ
    -0.11
     매우
    -0.11
     erittäin
    -0.11
    POSITIVE LOGITS
    天天看
    0.12
    俺也
    0.09
    估
    0.09
    以
    0.09
     laatst
    0.09
    真的假的
    0.09
     bestimmt
    0.08
    晓
    0.08
     calcium
    0.08
    TM
    0.08
    Activations Density 0.027%

    No Known Activations