© 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. 19-RESID-POST-AA
    11. 18934
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     perhaps
    -0.09
    some
    -0.09
     Guardia
    -0.09
     Perhaps
    -0.09
     或
    -0.08
     Maybe
    -0.08
     లేదా
    -0.08
     oldukça
    -0.08
    Perhaps
    -0.08
    Some
    -0.08
    POSITIVE LOGITS
    提高
    0.15
     betere
    0.15
     बेहतर
    0.14
     ลด
    0.14
     bessere
    0.14
     improve
    0.13
     improved
    0.13
     better
    0.13
     reduce
    0.13
     улучш
    0.13
    Activations Density 0.056%

    No Known Activations