© 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. 19-RESID-POST-AA
    11. 20896
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Academ
    -0.08
     оказ
    -0.07
     initiation
    -0.07
     आवश्यक
    -0.07
     prépare
    -0.07
    reci
    -0.07
     Siz
    -0.07
    oraus
    -0.07
     подготов
    -0.07
     prepar
    -0.07
    POSITIVE LOGITS
     મધ
    0.13
     ಮಧ್ಯ
    0.12
    Mid
    0.12
    (mid
    0.12
    _mid
    0.11
     mid
    0.11
     Mid
    0.11
    mid
    0.11
     midpoint
    0.11
    -middle
    0.11
    Activations Density 0.002%

    No Known Activations