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. 119116
    Prev
    Next
    INDEX
    Explanations

    run/led

    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
     sted
    -0.08
     Andrew
    -0.08
    anm
    -0.07
     Сонымен
    -0.07
     Кроме
    -0.07
    Кроме
    -0.07
     flour
    -0.07
    176
    -0.07
    azit
    -0.07
     เข้า
    -0.07
    POSITIVE LOGITS
     ')'
    0.08
    洞
    0.08
     scary
    0.08
     Kashmir
    0.07
     দিন
    0.07
     Cosmos
    0.07
     descon
    0.07
     Magnet
    0.07
     संच
    0.07
    日は
    0.07
    Activations Density 0.021%

    No Known Activations