© 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. 7885
    Prev
    Next
    INDEX
    Explanations

    Everyday applications and explanations

    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
     रिक
    -0.08
     ใหม่
    -0.08
     सर्वो
    -0.08
     श्रेष्ठ
    -0.08
     puree
    -0.08
     chodzi
    -0.08
    สมาชิก
    -0.08
     Vessel
    -0.08
     newcomer
    -0.08
    _clone
    -0.08
    POSITIVE LOGITS
     everyday
    0.15
     sehari
    0.13
     Everyday
    0.12
     cotidiana
    0.12
    每天
    0.10
     cotid
    0.10
     routinely
    0.10
     cotidiano
    0.10
     ubiquitous
    0.10
     countless
    0.10
    Activations Density 0.094%

    No Known Activations