© 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. 69772
    Prev
    Next
    INDEX
    Explanations

    acronyms

    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
     clients
    -0.08
     decks
    -0.08
     repart
    -0.07
    560
    -0.07
    815
    -0.07
    525
    -0.07
    (cs
    -0.07
    Judge
    -0.07
    270
    -0.07
    เจ้
    -0.07
    POSITIVE LOGITS
     удовольствием
    0.09
    0.08
    ্ৰ
    0.08
     begrip
    0.08
    ῦ
    0.08
     Diameter
    0.08
     Radius
    0.07
     удостовер
    0.07
     ಎಂದು
    0.07
    վա
    0.07
    Activations Density 0.029%
    No Known Activations