© 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. 70241
    Prev
    Next
    INDEX
    Explanations

    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
     Capitol
    -0.08
    -0.07
     Hassan
    -0.07
    利用
    -0.07
     hadir
    -0.07
     Digi
    -0.07
     hals
    -0.07
     Mohamed
    -0.07
    aman
    -0.07
     le
    -0.07
    POSITIVE LOGITS
     specifies
    0.09
     mặc
    0.09
     지정
    0.09
     defaults
    0.09
    設定
    0.09
    ilecek
    0.09
    specified
    0.09
    Customization
    0.09
     customization
    0.09
     specified
    0.08
    Activations Density 0.024%
    No Known Activations