© 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. 8003
    Prev
    Next
    INDEX
    Explanations

    ite

    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
    CREMENT
    -0.10
     feeling
    -0.08
     exemplary
    -0.08
    crement
    -0.08
     conserved
    -0.08
    311
    -0.08
     exposition
    -0.07
    crements
    -0.07
     Abr
    -0.07
    ומ
    -0.07
    POSITIVE LOGITS
     photovolta
    0.08
     cerveau
    0.08
    骗局
    0.08
     optics
    0.08
     erfre
    0.08
     drones
    0.08
     cocktails
    0.08
     factories
    0.08
     vrol
    0.08
    ják
    0.08
    Activations Density 0.001%

    No Known Activations