© 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. 64317
    Prev
    Next
    INDEX
    Explanations

    calendar math

    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
     fabs
    -0.08
     hobbies
    -0.08
     resign
    -0.08
    兴趣
    -0.08
     conced
    -0.07
     forks
    -0.07
     segreg
    -0.07
     wid
    -0.07
     उत्प
    -0.07
    emus
    -0.07
    POSITIVE LOGITS
     cyc
    0.10
     cyclic
    0.09
     индекс
    0.08
    ட்
    0.08
     ნიშნ
    0.08
     случая
    0.08
     биз
    0.08
     Tuk
    0.08
     niin
    0.08
     დავით
    0.08
    Activations Density 0.018%

    No Known Activations