© 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. 29402
    Prev
    Next
    INDEX
    Explanations

    automated systems

    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
     izj
    -0.09
     نقش
    -0.08
    נחנו
    -0.08
     contexte
    -0.08
     entlang
    -0.08
     cada
    -0.08
     contexto
    -0.08
     fabricante
    -0.08
     sommes
    -0.08
     المؤسسة
    -0.08
    POSITIVE LOGITS
    ikers
    0.09
     triggers
    0.08
     triggering
    0.08
    Stop
    0.08
    /hooks
    0.08
     triggered
    0.08
     STOP
    0.07
    หย
    0.07
     Stop
    0.07
    (stop
    0.07
    Activations Density 0.005%

    No Known Activations