© 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. 43028
    Prev
    Next
    INDEX
    Explanations

    General English text

    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
    ોએ
    -0.08
    /com
    -0.08
    /component
    -0.08
     Buckingham
    -0.08
     مرحله
    -0.08
     parfaite
    -0.08
     Armen
    -0.07
     Catarina
    -0.07
     آغاز
    -0.07
     beziehungsweise
    -0.07
    POSITIVE LOGITS
     object
    0.08
     siun
    0.08
    Txn
    0.08
     baby
    0.08
     Trotzdem
    0.08
    .EMAIL
    0.07
     election
    0.07
    ursing
    0.07
    oter
    0.07
     dennoch
    0.07
    Activations Density 0.000%

    No Known Activations