© 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. 94589
    Prev
    Next
    INDEX
    Explanations

    Cosine and sine

    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
     burgers
    -0.09
    insurance
    -0.08
     personalization
    -0.08
    AD
    -0.08
    /preferences
    -0.08
     paying
    -0.08
     spacecraft
    -0.08
     modify
    -0.08
     seamless
    -0.08
     caregivers
    -0.07
    POSITIVE LOGITS
     anpil
    0.09
     Colt
    0.08
     Nos
    0.08
    (pi
    0.08
     pi
    0.08
    ajan
    0.08
     Ali
    0.08
     π
    0.08
    алют
    0.08
     Twelve
    0.08
    Activations Density 0.021%

    No Known Activations