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. 60888
    Prev
    Next
    INDEX
    Explanations

    escape characters

    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
     SWOT
    -0.09
     Lending
    -0.08
     बाजार
    -0.08
     시장
    -0.08
     ESG
    -0.08
     hubs
    -0.08
     Sphere
    -0.08
     Kampala
    -0.08
     股
    -0.08
    Sphere
    -0.07
    POSITIVE LOGITS
     '\\
    0.11
    ('\\
    0.10
    _escape
    0.10
    ("\\
    0.09
     escapes
    0.09
     recognized
    0.09
     accepted
    0.09
     escape
    0.09
    字符
    0.09
    _unicode
    0.09
    Activations Density 0.004%

    No Known Activations