© 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. 112675
    Prev
    Next
    INDEX
    Explanations

    code addresses

    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
     emotional
    -0.09
     emotion
    -0.08
     bate
    -0.08
    统
    -0.07
     Emotional
    -0.07
     feelings
    -0.07
     sif
    -0.07
     timeline
    -0.07
    GUILayout
    -0.07
    .timeline
    -0.07
    POSITIVE LOGITS
     adjustable
    0.11
     Adjustable
    0.10
     المقا
    0.09
     configurable
    0.09
    MHz
    0.09
     بلو
    0.08
     CLOSED
    0.08
     configuración
    0.08
     knobs
    0.08
     Uncomment
    0.08
    Activations Density 0.004%

    No Known Activations