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. 42110
    Prev
    Next
    INDEX
    Explanations

    newline

    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
     sal
    -0.07
     humble
    -0.07
     scam
    -0.07
     mom
    -0.07
     Ernest
    -0.07
     Lore
    -0.07
     ramb
    -0.07
    IMM
    -0.07
     blogging
    -0.07
     bir
    -0.07
    POSITIVE LOGITS
    /reference
    0.08
    orgen
    0.08
     때문에
    0.08
    /title
    0.08
    /Header
    0.08
     powerhouse
    0.08
     opgeb
    0.08
    ▼
    0.07
     miatt
    0.07
    OTA
    0.07
    Activations Density 0.005%

    No Known Activations