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. 113776
    Prev
    Next
    INDEX
    Explanations

    stores

    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
     추진
    -0.09
     visualizar
    -0.08
    visual
    -0.08
     pend
    -0.08
     detach
    -0.08
     жаса
    -0.08
     suites
    -0.08
    ikte
    -0.07
     иници
    -0.07
    andre
    -0.07
    POSITIVE LOGITS
    店
    0.10
    允
    0.09
    商品
    0.09
    特色
    0.09
     прода
    0.09
    老板
    0.09
     aturan
    0.09
     bakery
    0.08
    仕様
    0.08
    售价
    0.08
    Activations Density 0.038%

    No Known Activations