© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 68099
    Prev
    Next
    INDEX
    Explanations

    COVID-19 medical texts

    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
    .struts
    -0.09
     Tcl
    -0.09
     Raster
    -0.08
     Freud
    -0.08
     unat
    -0.08
    Raster
    -0.08
    .osgi
    -0.08
     Ogre
    -0.08
    .awt
    -0.08
    .gwt
    -0.08
    POSITIVE LOGITS
     COVID
    0.22
    COVID
    0.21
     SARS
    0.19
     Covid
    0.19
     covid
    0.18
    Covid
    0.17
     코로나
    0.17
     कोविड
    0.16
     coronavirus
    0.16
     pandemic
    0.16
    Activations Density 0.019%

    No Known Activations