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. 11923
    Prev
    Next
    INDEX
    Explanations

    Protests and strikes

    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
     preprocess
    -0.08
     reused
    -0.08
     duplicate
    -0.07
     Windows
    -0.07
     you'll
    -0.07
     recomp
    -0.07
    ుడ
    -0.07
    'environnement
    -0.07
    ായ്
    -0.07
     environment
    -0.07
    POSITIVE LOGITS
     protesting
    0.16
     protest
    0.15
     احتجاج
    0.14
     protesta
    0.14
     protests
    0.12
     protested
    0.12
    宣布
    0.12
     പ്രതിഷേധ
    0.11
     boycott
    0.11
     refusal
    0.11
    Activations Density 0.041%

    No Known Activations