© 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. 71414
    Prev
    Next
    INDEX
    Explanations

    databases and data

    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
    oked
    -0.09
    ोद
    -0.08
     Angeb
    -0.07
     canceled
    -0.07
     Murray
    -0.07
    炮
    -0.07
     Rabatt
    -0.07
     Raman
    -0.07
     Passion
    -0.07
    Canceled
    -0.07
    POSITIVE LOGITS
     Populate
    0.10
    population
    0.10
     데이터를
    0.10
    sample
    0.09
     populous
    0.09
     samples
    0.09
     inhoud
    0.09
     sample
    0.09
    _SAMPLE
    0.09
    _samples
    0.09
    Activations Density 0.013%

    No Known Activations