© 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. 69298
    Prev
    Next
    INDEX
    Explanations

    carry

    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
     перев
    -0.08
     означает
    -0.07
    mless
    -0.07
     blokk
    -0.07
    ushing
    -0.07
     inflamm
    -0.07
     Englisch
    -0.07
    uded
    -0.07
     vivere
    -0.07
     bahasa
    -0.07
    POSITIVE LOGITS
    0.08
    Tu
    0.08
     folgend
    0.08
     Richtung
    0.08
    away
    0.08
    -away
    0.08
     podrás
    0.08
    Away
    0.08
     rumours
    0.08
    Quelques
    0.08
    Activations Density 0.004%
    No Known Activations