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. 119195
    Prev
    Next
    INDEX
    Explanations

    关键

    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
     statu
    -0.07
     Provide
    -0.07
    Ml
    -0.07
     Pref
    -0.07
     Such
    -0.07
     apporter
    -0.07
     versus
    -0.07
     deslig
    -0.06
     component
    -0.06
     ekip
    -0.06
    POSITIVE LOGITS
     række
    0.09
     引
    0.08
    enged
    0.08
    Ц
    0.08
     extracts
    0.08
    ggie
    0.08
    -provoking
    0.08
     Суд
    0.08
     غني
    0.08
    引
    0.08
    Activations Density 0.003%

    No Known Activations