© 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. 19-RESID-POST-AA
    11. 103432
    Prev
    Next
    INDEX
    Explanations

    usage

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     efficaces
    -0.08
    ↓
    -0.08
    akanaka
    -0.07
    elfalt
    -0.07
     निर्णय
    -0.07
    落实
    -0.07
     efficacement
    -0.07
     Entscheid
    -0.07
    ․
    -0.07
     ↓
    -0.07
    POSITIVE LOGITS
     الاستخدام
    0.19
     használ
    0.16
     repeated
    0.16
     usage
    0.16
     gebruikt
    0.15
     frequent
    0.15
     uso
    0.15
     ഉപയോഗ
    0.15
     sử
    0.15
     uży
    0.15
    Activations Density 0.012%

    No Known Activations