© 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. 69837
    Prev
    Next
    INDEX
    Explanations

    ased

    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
     bisher
    -0.08
     retrospect
    -0.08
    거
    -0.08
    รู้
    -0.08
     cited
    -0.07
     supposed
    -0.07
     Giant
    -0.07
    Miner
    -0.07
     TOO
    -0.07
     showing
    -0.07
    POSITIVE LOGITS
     tubular
    0.08
     scoreboard
    0.07
     Js
    0.07
     realiza
    0.07
     bloco
    0.07
     сайте
    0.07
     appointment
    0.07
    -ж
    0.07
    інде
    0.07
    дел
    0.07
    Activations Density 0.001%

    No Known Activations