© 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. 91757
    Prev
    Next
    INDEX
    Explanations

    网络

    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
    લ્લેખ
    -0.09
    (short
    -0.09
     Iceland
    -0.08
    ંપ
    -0.08
    	short
    -0.08
     short
    -0.08
     plur
    -0.08
    short
    -0.08
    ૂડ
    -0.08
    পুর
    -0.07
    POSITIVE LOGITS
     cybersecurity
    0.12
     безопасности
    0.10
    Cyber
    0.10
     सुरक्षा
    0.10
    Security
    0.09
     beveilig
    0.09
     безопасность
    0.09
     veiligheid
    0.09
     ಸುರ
    0.09
     safeguarding
    0.09
    Activations Density 0.003%

    No Known Activations