© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54701
    Prev
    Next
    INDEX
    Explanations

    weapons of mass destruction

    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
     pigeon
    -0.08
     Keyboard
    -0.08
     Reduce
    -0.07
     recib
    -0.07
     Essence
    -0.07
     couvert
    -0.07
    -0.07
     baja
    -0.07
     Vk
    -0.07
    /Base
    -0.07
    POSITIVE LOGITS
    ontas
    0.09
    汤
    0.09
    '
    0.08
    onstr
    0.08
     Mannheim
    0.08
    PLI
    0.08
     hypothetical
    0.08
     refres
    0.08
    0.08
    -li
    0.07
    Activations Density 0.008%
    No Known Activations