© 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. 17993
    Prev
    Next
    INDEX
    Explanations

    code and logic errors

    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
    ებიდან
    -0.12
    იული
    -0.11
     ունեցող
    -0.11
    იდან
    -0.11
    yndaky
    -0.10
     qq天天中彩票
    -0.10
    unniit
    -0.10
    ից
    -0.10
    ներից
    -0.10
    յան
    -0.10
    POSITIVE LOGITS
    .W
    0.08
    .wave
    0.07
    .j
    0.07
     also
    0.07
    その他
    0.07
     "
    0.07
     planning
    0.07
    .htm
    0.07
    .wav
    0.07
     drawings
    0.07
    Activations Density 0.000%

    No Known Activations