© 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. 112527
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
     близ
    -0.08
     ставка
    -0.08
     kaf
    -0.08
     press
    -0.08
    _ERROR
    -0.08
     لع
    -0.08
     ثق
    -0.08
     باسم
    -0.07
     устро
    -0.07
     حجم
    -0.07
    POSITIVE LOGITS
    restrict
    0.09
     intersect
    0.09
    requirements
    0.09
    subset
    0.09
     subset
    0.09
     Combine
    0.08
     intersection
    0.08
    Combine
    0.08
    valid
    0.08
     imposed
    0.08
    Activations Density 0.064%

    No Known Activations