© 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. 15-RESID-POST-AA
    11. 16523
    Prev
    Next
    INDEX
    Explanations

    financial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _security
    -0.09
     सुरक्षा
    -0.09
     الأمنية
    -0.09
    าศ
    -0.08
    安心
    -0.08
     privacy
    -0.08
     seguridad
    -0.08
     मिलने
    -0.08
     security
    -0.08
     Privacy
    -0.08
    POSITIVE LOGITS
    财政
    0.13
     poor
    0.12
     ухуд
    0.12
     inefficient
    0.12
     Poor
    0.11
     ineff
    0.11
    Poor
    0.11
     ineffective
    0.11
     hardships
    0.11
     inadequ
    0.11
    Activations Density 0.009%

    No Known Activations