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. 45625
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     outgoing
    -0.08
     Websites
    -0.07
    Outgoing
    -0.07
     Morning
    -0.07
    ඩ
    -0.07
     contention
    -0.07
    همة
    -0.07
    ’ident
    -0.07
    Website
    -0.07
     succeeded
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.09
    ullah
    0.08
    ,以及
    0.07
     }],↵
    0.07
     Receiver
    0.07
     بالإضافة
    0.07
     และ
    0.07
    aup
    0.07
    ラク
    0.07
     (($
    0.07
    Activations Density 0.022%

    No Known Activations