© 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 EvalsExportsinterp-engineNEWAPI 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. 70127
    Prev
    Next
    INDEX
    Explanations

    reflections

    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
     باشد
    -0.09
     acer
    -0.07
     redefine
    -0.07
     moder
    -0.07
     standards
    -0.07
     باشند
    -0.07
     redact
    -0.07
    €
    -0.07
     corrig
    -0.07
     ɔ
    -0.07
    POSITIVE LOGITS
    得到
    0.11
     Dabei
    0.10
     Dadurch
    0.09
     yields
    0.09
    即可
    0.08
    warts
    0.08
    遇
    0.08
     מנת
    0.08
    看看
    0.08
     чтобы
    0.08
    Activations Density 0.105%

    No Known Activations