© 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. 71811
    Prev
    Next
    INDEX
    Explanations

    probability multiplication

    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
     elected
    -0.09
    bag
    -0.08
     enlarg
    -0.08
    šča
    -0.08
    EDS
    -0.08
    .which
    -0.08
    Bag
    -0.08
     stimulates
    -0.08
     threw
    -0.08
    жал
    -0.08
    POSITIVE LOGITS
     probability
    0.13
     probabilities
    0.13
     Probability
    0.12
    _probability
    0.11
    Probability
    0.11
    概率
    0.10
     compounded
    0.10
     conditional
    0.10
     conditioned
    0.10
     improbable
    0.10
    Activations Density 0.026%

    No Known Activations