© 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. 69849
    Prev
    Next
    INDEX
    Explanations

    H. pylori

    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
    .parents
    -0.08
     Reis
    -0.08
    ziplin
    -0.08
     Kijk
    -0.08
    ='\
    -0.08
    igail
    -0.08
    cloth
    -0.07
    =test
    -0.07
     Kirch
    -0.07
     ROUT
    -0.07
    POSITIVE LOGITS
     installed
    0.08
     infection
    0.08
     WHO
    0.08
     설치
    0.08
     installation
    0.08
    感染
    0.08
     ontst
    0.08
     cultivar
    0.08
     instalado
    0.08
     entero
    0.07
    Activations Density 0.002%

    No Known Activations