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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 49100
    Prev
    Next
    INDEX
    Explanations

    Already happening

    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
     reagent
    -0.08
    obb
    -0.08
     rue
    -0.07
    마다
    -0.07
    pk
    -0.07
    pers
    -0.07
     vraiment
    -0.07
    ね
    -0.07
     Pause
    -0.07
    berg
    -0.07
    POSITIVE LOGITS
     already
    0.14
    already
    0.13
     tẹlẹ
    0.13
     zaten
    0.12
     bereits
    0.12
     Already
    0.12
    Already
    0.12
     بالفعل
    0.12
     ήδη
    0.11
     déjà
    0.11
    Activations Density 0.115%

    No Known Activations