© 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. 47421
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
     quân
    -0.08
     derrot
    -0.08
     refund
    -0.08
    iew
    -0.08
     derrota
    -0.08
     retiro
    -0.07
    Immutable
    -0.07
    refund
    -0.07
    avourite
    -0.07
    Relevant
    -0.07
    POSITIVE LOGITS
     conexión
    0.08
    -mediated
    0.08
    连接
    0.08
     conexion
    0.08
     conectar
    0.08
     Glam
    0.08
     conecta
    0.07
     vocals
    0.07
     connecter
    0.07
     coupling
    0.07
    Activations Density 0.001%

    No Known Activations