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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 29985
    Prev
    Next
    INDEX
    Explanations

    Roosevelt

    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
     cloth
    -0.07
    (st
    -0.07
     refr
    -0.07
    &t
    -0.07
     lockdown
    -0.07
     غرفة
    -0.07
     حلول
    -0.07
    .javascript
    -0.07
    装
    -0.07
     ts
    -0.07
    POSITIVE LOGITS
    一种
    0.09
    क्का
    0.08
     RHS
    0.08
     Akk
    0.08
    מן
    0.08
     凤
    0.08
    Ela
    0.08
     jerk
    0.08
    remely
    0.08
     pon
    0.08
    Activations Density 0.001%

    No Known Activations