© 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. 11-RESID-POST-AA
    11. 71461
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    仔
    -0.08
    Scalar
    -0.08
    _internal
    -0.08
     angla
    -0.08
     unconditional
    -0.08
     unspecified
    -0.08
    England
    -0.08
     kø
    -0.07
    Anne
    -0.07
    Searcher
    -0.07
    POSITIVE LOGITS
     स्मार्ट
    0.09
     上传
    0.09
     automáticamente
    0.09
    上传
    0.09
     automaticamente
    0.09
     livestream
    0.09
     스마트
    0.09
     automatisch
    0.09
     แชร์
    0.09
    预约
    0.09
    Activations Density 0.075%

    No Known Activations