© 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. 68952
    Prev
    Next
    INDEX
    Explanations

    kick

    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
     inadvertently
    -0.09
     desto
    -0.08
     ileti
    -0.07
     newsletter
    -0.07
     HMS
    -0.07
     organizing
    -0.07
    elist
    -0.07
    hp
    -0.07
     apparaît
    -0.07
     hran
    -0.07
    POSITIVE LOGITS
     امتح
    0.09
     Seat
    0.08
    经典
    0.08
     Come
    0.08
     unidade
    0.08
     Pat
    0.07
     medewerker
    0.07
     COMPONENT
    0.07
     klassischen
    0.07
     Klasse
    0.07
    Activations Density 0.006%

    No Known Activations