© 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. 108313
    Prev
    Next
    INDEX
    Explanations

    sum of three squares theorem

    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
     movement
    -0.08
     efficiencies
    -0.08
     cohesion
    -0.08
     Movement
    -0.07
     balm
    -0.07
     sos
    -0.07
     contact
    -0.07
     functions
    -0.07
    Movement
    -0.07
    tery
    -0.07
    POSITIVE LOGITS
     forb
    0.09
     prohibits
    0.09
    禁止
    0.09
     forbid
    0.09
     prohibit
    0.08
     famously
    0.08
     prohib
    0.08
     禁
    0.08
     aturan
    0.08
    资格
    0.08
    Activations Density 0.004%

    No Known Activations