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. 106174
    Prev
    Next
    INDEX
    Explanations

    digital art

    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
     시민
    -0.09
     SQLException
    -0.09
    	connection
    -0.09
     medico
    -0.08
     sensing
    -0.08
     cinemas
    -0.08
     tenancy
    -0.08
     Sehens
    -0.08
    施設
    -0.08
     시설
    -0.08
    POSITIVE LOGITS
     cartoon
    0.13
     Cartoon
    0.12
    Adobe
    0.11
    动漫
    0.11
     Illustrator
    0.11
     illustrator
    0.11
     Adobe
    0.11
     watercolor
    0.11
     digitally
    0.10
     anime
    0.10
    Activations Density 0.015%

    No Known Activations