© 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 EvalsExportsAPI 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. 63511
    Prev
    Next
    INDEX
    Explanations

    feel

    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
     aller
    -0.08
    oder
    -0.08
    Ө
    -0.07
     Excellence
    -0.07
    -being
    -0.07
     জীবন
    -0.07
    _des
    -0.07
     Auss
    -0.07
     Dermat
    -0.07
    interesting
    -0.07
    POSITIVE LOGITS
     refreshed
    0.08
    قه
    0.08
     क्व
    0.08
     autón
    0.07
     الحجر
    0.07
     inviting
    0.07
     tón
    0.07
     tune
    0.07
     tang
    0.07
     tame
    0.07
    Activations Density 0.009%

    No Known Activations