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. 117510
    Prev
    Next
    INDEX
    Explanations

    level

    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
     Cav
    -0.09
     Viv
    -0.08
     결국
    -0.08
    -0.08
    Viv
    -0.08
     Ita
    -0.08
    tod
    -0.07
    duino
    -0.07
     мор
    -0.07
    ługi
    -0.07
    POSITIVE LOGITS
     synonymous
    0.08
     गु
    0.08
     entity
    0.08
     intertw
    0.08
    いう
    0.07
     refin
    0.07
    别
    0.07
     co
    0.07
     enforce
    0.07
     intertwined
    0.07
    Activations Density 0.017%

    No Known Activations