© 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. 44861
    Prev
    Next
    INDEX
    Explanations

    Succulents and plants

    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
     girls
    -0.09
     teachers
    -0.08
     bilingual
    -0.08
     dags
    -0.07
    tmpl
    -0.07
    教師
    -0.07
    站
    -0.07
     decks
    -0.07
     Pall
    -0.07
    mentar
    -0.07
    POSITIVE LOGITS
     малень
    0.09
     tiny
    0.08
     веч
    0.08
     ornamental
    0.08
     CIM
    0.08
     cobra
    0.08
     Autodesk
    0.08
     контак
    0.08
     мал
    0.08
     råd
    0.07
    Activations Density 0.019%

    No Known Activations