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. 90238
    Prev
    Next
    INDEX
    Explanations

    sem

    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
    hte
    -0.08
     stark
    -0.08
     sicht
    -0.08
     gli
    -0.08
     narrowly
    -0.07
     mandate
    -0.07
     Ther
    -0.07
    的重要
    -0.07
    VISIBLE
    -0.07
    	Check
    -0.07
    POSITIVE LOGITS
     fractions
    0.08
    onomy
    0.08
     dagger
    0.07
    imum
    0.07
    imp
    0.07
    大利
    0.07
    ımız
    0.07
     største
    0.07
     despre
    0.07
    ical
    0.07
    Activations Density 0.001%

    No Known Activations