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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 29377
    Prev
    Next
    INDEX
    Explanations

    fluids and displacement

    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
     related
    -0.08
    命
    -0.08
    ，你
    -0.07
    Who's
    -0.07
    Dispatch
    -0.07
     retrospect
    -0.07
     yourself
    -0.07
     you're
    -0.07
    群
    -0.07
     embellished
    -0.07
    POSITIVE LOGITS
     cavities
    0.12
     evacuated
    0.10
     deficit
    0.09
     syringe
    0.09
     pristine
    0.09
     occupants
    0.09
     fillings
    0.09
     જમી
    0.09
     poured
    0.09
     occupancy
    0.09
    Activations Density 0.006%

    No Known Activations