Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 76306
    Prev
    Next
    INDEX
    Explanations

    coma

    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
     thấy
    -0.07
     gn
    -0.07
     dotted
    -0.07
     delegated
    -0.07
     saut
    -0.07
     decorate
    -0.07
     gê
    -0.07
     sloppy
    -0.07
     bikin
    -0.07
     odstr
    -0.07
    POSITIVE LOGITS
     долго
    0.09
     rehabilitation
    0.09
     կոմ
    0.09
     კომ
    0.08
    Kami
    0.08
     coma
    0.08
     קומ
    0.08
    Sinds
    0.08
     түш
    0.08
    amız
    0.08
    Activations Density 0.019%

    No Known Activations