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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70161
    Prev
    Next
    INDEX
    Explanations

    Upward body movement

    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
    	wait
    -0.08
     exponential
    -0.08
     quotation
    -0.07
    צט
    -0.07
    _quote
    -0.07
     evolutionary
    -0.07
     بیٹھ
    -0.07
    Formula
    -0.07
     wait
    -0.07
     часов
    -0.07
    POSITIVE LOGITS
     üle
    0.09
     피부
    0.08
     обслед
    0.08
     SYSTEM
    0.08
     COUNTRY
    0.08
     bienestar
    0.08
     lungs
    0.08
     Damage
    0.08
     limbs
    0.08
    棚
    0.08
    Activations Density 0.006%

    No Known Activations