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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29519
    Prev
    Next
    INDEX
    Explanations

    person

    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
     together
    -0.09
    Together
    -0.08
     Ressourcen
    -0.08
    ંગ્ર
    -0.08
    dominal
    -0.08
     samen
    -0.07
    Oj
    -0.07
     zusammen
    -0.07
    322
    -0.07
    asio
    -0.07
    POSITIVE LOGITS
    _COST
    0.09
     Costs
    0.09
    Costo
    0.09
    ™↵↵
    0.09
     costes
    0.09
     coste
    0.09
     costo
    0.09
     costing
    0.09
    ™,
    0.09
     koszt
    0.08
    Activations Density 0.023%

    No Known Activations