© 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. 110006
    Prev
    Next
    INDEX
    Explanations

    data visualization packages

    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
    Negative Logits
     relocating
    -0.08
     пла
    -0.08
    NAS
    -0.07
    Cancellation
    -0.07
    nonce
    -0.07
     placing
    -0.07
    _terms
    -0.07
    pane
    -0.07
     перест
    -0.07
    pty
    -0.07
    POSITIVE LOGITS
    avait
    0.09
     swal
    0.07
    black
    0.07
    ательного
    0.07
     potenci
    0.07
    avadoc
    0.07
     д
    0.07
    -black
    0.07
     talál
    0.07
    �
    0.07
    Activations Density 0.003%

    No Known Activations