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. 55152
    Prev
    Next
    INDEX
    Explanations

    day

    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
     plt
    -0.10
    plt
    -0.09
     odp
    -0.08
    	plt
    -0.08
    ccak
    -0.07
    Overlay
    -0.07
    plib
    -0.07
    mäßig
    -0.07
     outf
    -0.07
     potř
    -0.07
    POSITIVE LOGITS
     countless
    0.08
     ежедневно
    0.08
     diariamente
    0.08
    (日
    0.08
     voorkomende
    0.08
     findes
    0.08
    ുണ്ട്
    0.08
     plaatsvinden
    0.08
     constantemente
    0.07
     Renee
    0.07
    Activations Density 0.034%

    No Known Activations