© 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. 19-RESID-POST-AA
    11. 19489
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Few
    -0.08
    asse
    -0.08
     hơn
    -0.07
     více
    -0.07
    Rut
    -0.07
     consisting
    -0.07
    _rows
    -0.07
     Totally
    -0.07
    ulur
    -0.07
     wholly
    -0.07
    POSITIVE LOGITS
     ursprüng
    0.10
     alvast
    0.10
     ursprünglich
    0.10
     ήδη
    0.10
     awal
    0.09
    」という
    0.09
     oorspronkelijke
    0.09
     初
    0.09
    初
    0.09
     inicial
    0.09
    Activations Density 0.002%

    No Known Activations