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. 30190
    Prev
    Next
    INDEX
    Explanations

    wide

    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
     Kug
    -0.09
     Trois
    -0.08
    atre
    -0.08
    uate
    -0.08
     Goldman
    -0.08
    osex
    -0.08
     endot
    -0.08
     Bish
    -0.07
     Liberty
    -0.07
     Padre
    -0.07
    POSITIVE LOGITS
    -ranging
    0.15
    泛
    0.10
    -reaching
    0.10
     çap
    0.10
     جدًا
    0.09
     спект
    0.09
    -bodied
    0.09
    artig
    0.08
     прог
    0.08
    范围
    0.08
    Activations Density 0.027%

    No Known Activations