© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7658
    Prev
    Next
    INDEX
    Explanations

    tilde

    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
     probing
    -0.08
    elly
    -0.08
    betr
    -0.08
    /query
    -0.08
     ব্য
    -0.07
    (prob
    -0.07
     dissol
    -0.07
    /testing
    -0.07
     rezerv
    -0.07
     relativ
    -0.07
    POSITIVE LOGITS
    253
    0.08
    251
    0.08
    Offer
    0.07
    Plots
    0.07
    offer
    0.07
    алим
    0.07
    ();
↵
    0.07
     hué
    0.07
     visitante
    0.07
    चारी
    0.07
    Activations Density 0.003%

    No Known Activations