© 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. 22901
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     debemos
    -0.10
     devemos
    -0.10
     such
    -0.10
     zulke
    -0.09
     precisamos
    -0.08
    such
    -0.08
     we're
    -0.08
     we'll
    -0.08
     ನಾವು
    -0.08
     we'd
    -0.08
    POSITIVE LOGITS
     customize
    0.16
     customized
    0.15
    _customize
    0.14
    Customize
    0.14
     customizing
    0.13
     Customize
    0.12
     uitgebreid
    0.12
     optar
    0.12
    Customized
    0.12
     customise
    0.11
    Activations Density 0.011%

    No Known Activations