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. 49081
    Prev
    Next
    INDEX
    Explanations

    cigar

    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
     crucial
    -0.08
     प्रतिस
    -0.08
     compre
    -0.08
     bindings
    -0.07
     XMLHttp
    -0.07
     irrigation
    -0.07
     skipper
    -0.07
     validation
    -0.07
     irrig
    -0.07
     embod
    -0.07
    POSITIVE LOGITS
     pensamiento
    0.08
     tertiary
    0.08
     disfrutar
    0.08
     exaggerated
    0.08
    ablemente
    0.08
    Hil
    0.08
    李
    0.08
    Empleado
    0.08
     চিন
    0.08
     lounge
    0.07
    Activations Density 0.002%

    No Known Activations