© 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. 30256
    Prev
    Next
    INDEX
    Explanations

    app interfaces and mockups

    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
     വി�
    -0.09
     урож
    -0.09
     जोड़
    -0.09
     pigs
    -0.08
     образование
    -0.08
     छोड़
    -0.08
     усл
    -0.08
    ammad
    -0.07
     വിട്ട
    -0.07
     Unite
    -0.07
    POSITIVE LOGITS
     screenshot
    0.11
    截图
    0.09
    模拟
    0.09
     montr
    0.09
     screenshots
    0.09
     bezel
    0.09
     depicted
    0.09
     imagined
    0.08
    Screenshot
    0.08
     demos
    0.08
    Activations Density 0.012%

    No Known Activations