© 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. 129246
    Prev
    Next
    INDEX
    Explanations

    facial anatomy

    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
     freedoms
    -0.07
     Fähigkeiten
    -0.07
     Kent
    -0.07
     continually
    -0.07
     schop
    -0.07
     continuamente
    -0.07
     Fähigkeit
    -0.07
    .gl
    -0.07
    Kent
    -0.07
     θ
    -0.07
    POSITIVE LOGITS
     caval
    0.10
     antigo
    0.08
     elapsed
    0.08
     salient
    0.08
    merce
    0.08
    oung
    0.08
    udí
    0.08
    Adobe
    0.08
     mimi
    0.08
    Celebrity
    0.07
    Activations Density 0.004%

    No Known Activations