© 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. 63966
    Prev
    Next
    INDEX
    Explanations

    in

    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
     Myanmar
    -0.09
     quitting
    -0.09
     Syria
    -0.08
    કારે
    -0.08
     ក្នុង
    -0.08
     Faro
    -0.08
     FCA
    -0.08
     DS
    -0.08
    beitet
    -0.08
    ოლოგ
    -0.08
    POSITIVE LOGITS
     húmed
    0.10
     predis
    0.10
     humedad
    0.09
     влаж
    0.09
     susceptible
    0.09
     stagnant
    0.09
    Humidity
    0.08
     prone
    0.08
     sly
    0.08
     തുറ
    0.08
    Activations Density 0.021%

    No Known Activations