© 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 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. 63722
    Prev
    Next
    INDEX
    Explanations

    NASM assembly 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
    療
    -0.08
     glitches
    -0.07
     portfolio
    -0.07
     farm
    -0.07
    τ
    -0.07
     vốn
    -0.07
     rok
    -0.07
    Handlers
    -0.07
    portfolio
    -0.07
    Linda
    -0.07
    POSITIVE LOGITS
     requiere
    0.09
     требует
    0.09
     requires
    0.08
     يحتاج
    0.08
     требуется
    0.08
     потребуется
    0.08
     পরীক্ষ
    0.08
     принимает
    0.08
    _fragment
    0.08
    -lasting
    0.08
    Activations Density 0.001%

    No Known Activations