© 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 EvalsExportsinterp-engineNEWAPI 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. 110928
    Prev
    Next
    INDEX
    Explanations

    Aerodynamics/Dynamics

    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
    Kho
    -0.09
     hereditary
    -0.08
     bild
    -0.08
     Inicio
    -0.08
     wrestler
    -0.08
    对此
    -0.07
     兴
    -0.07
    Esto
    -0.07
    Fiber
    -0.07
     Đây
    -0.07
    POSITIVE LOGITS
     retrospect
    0.08
     studies
    0.08
     simulations
    0.08
    _metrics
    0.08
     caut
    0.08
     экспер
    0.08
     dynamics
    0.08
    raul
    0.08
    _properties
    0.08
     инжен
    0.08
    Activations Density 0.021%

    No Known Activations