© 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. 25024
    Prev
    Next
    INDEX
    Explanations

    Tea

    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
    ido
    -0.08
     stalking
    -0.08
    abetic
    -0.08
    -guid
    -0.08
    धी
    -0.07
    slow
    -0.07
     variability
    -0.07
    ري
    -0.07
    டிய
    -0.07
     slow
    -0.07
    POSITIVE LOGITS
     simulated
    0.10
     آز
    0.08
     boycott
    0.08
     Szen
    0.08
     বাব
    0.08
     downfall
    0.08
     demise
    0.08
     Tea
    0.08
     somos
    0.08
     sunk
    0.08
    Activations Density 0.001%

    No Known Activations