© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 933
    Prev
    Next
    INDEX
    Explanations

    carefully

    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
     Ibiza
    -0.08
    仅
    -0.08
     ink
    -0.07
     Esperanto
    -0.07
     referencia
    -0.07
     Ivan
    -0.07
     deixa
    -0.07
    dub
    -0.07
    &O
    -0.07
     aptly
    -0.07
    POSITIVE LOGITS
     craftsmanship
    0.09
     wording
    0.08
     footing
    0.08
    事项
    0.08
    estens
    0.08
    vuld
    0.08
    ৰে
    0.08
    Pk
    0.08
     interplay
    0.07
    ριά
    0.07
    Activations Density 0.016%

    No Known Activations