Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58585
    Prev
    Next
    INDEX
    Explanations

    :

    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
     aner
    -0.09
    лев
    -0.08
    âte
    -0.08
     vacancy
    -0.08
     tribal
    -0.08
     नेतृत्व
    -0.08
     constituted
    -0.08
     সংগ্র
    -0.08
     moż
    -0.08
    лт
    -0.07
    POSITIVE LOGITS
     tween
    0.10
     Blender
    0.09
     drunk
    0.08
    Animator
    0.08
    Lua
    0.08
     commented
    0.08
     extrusion
    0.08
    Tween
    0.08
     함수
    0.08
     drunken
    0.07
    Activations Density 0.009%

    No Known Activations