© 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. 54928
    Prev
    Next
    INDEX
    Explanations

    Jong

    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
     verliert
    -0.08
    alloween
    -0.08
    umming
    -0.08
    \modules
    -0.07
    iós
    -0.07
    alternative
    -0.07
    malıdır
    -0.07
     alternatives
    -0.07
     alternativas
    -0.07
    neet
    -0.07
    POSITIVE LOGITS
    习近平
    0.09
    总书记
    0.09
    եի
    0.09
    Govern
    0.08
    Schedule
    0.08
    ിന്റെ
    0.08
     governing
    0.08
     dirname
    0.08
    ինի
    0.08
     dirigir
    0.08
    Activations Density 0.006%

    No Known Activations