© 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. 111400
    Prev
    Next
    INDEX
    Explanations

    Hepatitis B

    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
     locality
    -0.09
     argparse
    -0.08
    routing
    -0.08
     Manhattan
    -0.08
     পো
    -0.08
    -tree
    -0.07
    menu
    -0.07
    name
    -0.07
     argument
    -0.07
    inerary
    -0.07
    POSITIVE LOGITS
     hepatitis
    0.11
     ಸೋಂಕ
    0.10
     HPV
    0.09
    病毒
    0.09
     titres
    0.09
    感染
    0.09
     infek
    0.09
     Africans
    0.08
     Persistent
    0.08
    790
    0.08
    Activations Density 0.007%

    No Known Activations