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. 58660
    Prev
    Next
    INDEX
    Explanations

    ambiguity/vagueness

    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
     gled
    -0.08
     draait
    -0.08
     Gastro
    -0.08
    Cru
    -0.08
     normalmente
    -0.08
     Pall
    -0.07
     Fro
    -0.07
    에
    -0.07
     Gast
    -0.07
     elde
    -0.07
    POSITIVE LOGITS
     अस्प
    0.16
    明确
    0.16
     clarity
    0.16
     ambiguity
    0.15
     clarification
    0.14
     claridad
    0.14
     clare
    0.14
     स्पष्ट
    0.14
    晰
    0.14
     ambigu
    0.14
    Activations Density 0.050%

    No Known Activations