© 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 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. 63444
    Prev
    Next
    INDEX
    Explanations

    scramble

    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
     поли
    -0.08
     Gly
    -0.08
     unos
    -0.08
     cấu
    -0.08
     Vas
    -0.07
    GST
    -0.07
    uds
    -0.07
     curing
    -0.07
     PSD
    -0.07
     огранич
    -0.07
    POSITIVE LOGITS
     scramble
    0.10
    ять
    0.08
     hedge
    0.08
     urgency
    0.08
     urgently
    0.08
     scrambled
    0.08
    Urg
    0.08
    �
    0.08
     دنبال
    0.07
     stimulant
    0.07
    Activations Density 0.002%

    No Known Activations