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. 112478
    Prev
    Next
    INDEX
    Explanations

    Role-playing dialogues and sequencing

    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
     Bade
    -0.07
     clubhouse
    -0.07
     factor
    -0.07
     inflammation
    -0.07
    Volumes
    -0.07
     injunction
    -0.07
    /drop
    -0.07
     catchy
    -0.07
    lega
    -0.07
     BUY
    -0.07
    POSITIVE LOGITS
     UAV
    0.08
     развед
    0.08
     Nakam
    0.08
     સેવ
    0.08
     Ether
    0.07
     katk
    0.07
     yür
    0.07
    Euler
    0.07
     मिट
    0.07
     juurde
    0.07
    Activations Density 0.001%

    No Known Activations