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. 112268
    Prev
    Next
    INDEX
    Explanations

    AR

    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
    alive
    -0.09
     birthplace
    -0.09
     boat
    -0.08
     cheaply
    -0.08
    ässer
    -0.08
    Alive
    -0.08
    راحی
    -0.07
    лод
    -0.07
     proposant
    -0.07
     thriving
    -0.07
    POSITIVE LOGITS
     correspondent
    0.08
    0.08
     vingers
    0.08
     impede
    0.07
     Kiss
    0.07
     kiss
    0.07
     scratching
    0.07
    ~/
    0.07
     retail
    0.07
     SDA
    0.07
    Activations Density 0.003%

    No Known Activations