© 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. 19-RESID-POST-AA
    11. 18071
    Prev
    Next
    INDEX
    Explanations

    下面

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    -existent
    -0.10
    -related
    -0.09
    -existing
    -0.09
    -positive
    -0.09
    ાયક
    -0.09
    -only
    -0.09
     other
    -0.09
    -empty
    -0.09
    -associated
    -0.09
     menudo
    -0.08
    POSITIVE LOGITS
    给
    0.13
    帮
    0.13
    下面
    0.12
    终于
    0.12
     вот
    0.11
    这样
    0.11
    是一
    0.11
    这里
    0.11
     제가
    0.11
    你
    0.11
    Activations Density 0.004%

    No Known Activations