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. 58490
    Prev
    Next
    INDEX
    Explanations

    a

    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
     homens
    -0.08
     congratulate
    -0.07
     Congressional
    -0.07
     uomini
    -0.07
    Captain
    -0.07
    orte
    -0.07
    ocusing
    -0.07
     mannen
    -0.07
     congressional
    -0.07
     marito
    -0.07
    POSITIVE LOGITS
     northeastern
    0.09
     southern
    0.09
    sou
    0.09
     atmosphere
    0.09
     southwestern
    0.09
     Snow
    0.08
     drain
    0.08
    空气
    0.08
     Tun
    0.08
     Jag
    0.07
    Activations Density 0.011%

    No Known Activations