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. 30520
    Prev
    Next
    INDEX
    Explanations

    chemistry

    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
    武
    -0.09
     payday
    -0.08
     Payday
    -0.08
     staircase
    -0.08
     спис
    -0.08
     PTSD
    -0.08
     школы
    -0.08
     Affiliate
    -0.08
    貼
    -0.08
     arrec
    -0.08
    POSITIVE LOGITS
     atmosphere
    0.11
    空气
    0.11
     воздуха
    0.11
     gases
    0.11
     airborne
    0.10
    Atmos
    0.10
     humidity
    0.10
     atmos
    0.10
     ambience
    0.10
     dioxide
    0.10
    Activations Density 0.011%

    No Known Activations