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. 78362
    Prev
    Next
    INDEX
    Explanations

    expensive

    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
     оч
    -0.08
    SEP
    -0.08
    тык
    -0.08
    VV
    -0.07
     Syl
    -0.07
     depression
    -0.07
     deposito
    -0.07
    зык
    -0.07
     கொண்ட
    -0.07
     посвящ
    -0.07
    POSITIVE LOGITS
    昂
    0.12
     expensive
    0.11
     للغاية
    0.09
     جدًا
    0.08
     hơn
    0.08
    osity
    0.08
    etry
    0.07
    ish
    0.07
     incurred
    0.07
     cl
    0.07
    Activations Density 0.027%

    No Known Activations