© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111548
    Prev
    Next
    INDEX
    Explanations

    Canva tutorials and code

    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
     plut
    -0.10
     CWE
    -0.09
     burglary
    -0.09
    Instrumentation
    -0.09
     penetrating
    -0.09
     infiltration
    -0.09
    Travers
    -0.08
     penetrate
    -0.08
     tunn
    -0.08
     burglar
    -0.08
    POSITIVE LOGITS
     Canva
    0.21
     Pinterest
    0.11
     erstellen
    0.10
     ઝડપી
    0.10
    快捷
    0.10
     Shutterstock
    0.10
     Klik
    0.10
     Fiverr
    0.10
    快速
    0.10
     રંગ
    0.10
    Activations Density 0.029%

    No Known Activations