© 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. 70203
    Prev
    Next
    INDEX
    Explanations

    or

    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
     milieu
    -0.08
     Glasgow
    -0.08
     kin
    -0.08
     pleasant
    -0.08
     relocation
    -0.07
     prostoru
    -0.07
     פני
    -0.07
    िंक
    -0.07
     ventilation
    -0.07
     coverings
    -0.07
    POSITIVE LOGITS
     કોઈ
    0.08
     любые
    0.08
    ئە
    0.07
     playa
    0.07
     Arbitr
    0.07
     किसी
    0.07
    න්න
    0.07
    ujem
    0.07
     테
    0.07
     તેઓ
    0.07
    Activations Density 0.003%

    No Known Activations