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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111702
    Prev
    Next
    INDEX
    Explanations

    instructions and guidelines

    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
     pesquisadores
    -0.09
     subjected
    -0.08
    }-${
    -0.08
    ன்ற
    -0.08
    }${
    -0.08
    окуп
    -0.08
    }.${
    -0.07
    =${
    -0.07
    -${
    -0.07
    )}>↵
    -0.07
    POSITIVE LOGITS
     clichés
    0.09
    CKET
    0.09
    wng
    0.08
    tionen
    0.08
    jit
    0.08
     کب
    0.08
     sjen
    0.08
     cili
    0.07
     clich
    0.07
     cliché
    0.07
    Activations Density 0.006%

    No Known Activations