© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70337
    Prev
    Next
    INDEX
    Explanations

    legal concepts

    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
    ેવ
    -0.09
    zlich
    -0.08
    Pas
    -0.07
    ورس
    -0.07
     Auburn
    -0.07
     implementing
    -0.07
    怎样
    -0.07
     hanger
    -0.07
     taza
    -0.07
     dispersion
    -0.07
    POSITIVE LOGITS
     आरोप
    0.09
     ಆರೋಪ
    0.09
     ситуацию
    0.08
     condemnation
    0.08
     seize
    0.08
     lass
    0.07
     arise
    0.07
     seized
    0.07
    _origin
    0.07
     bitten
    0.07
    Activations Density 0.010%

    No Known Activations