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. 43384
    Prev
    Next
    INDEX
    Explanations

    S

    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
    韓
    -0.07
     તરફ
    -0.07
    assin
    -0.07
    σει
    -0.07
    /security
    -0.07
    .Controllers
    -0.07
     avi
    -0.07
     根
    -0.07
    refu
    -0.07
    Safety
    -0.07
    POSITIVE LOGITS
     factorial
    0.10
     Pascal
    0.09
     catal
    0.08
    atakan
    0.08
     tableaux
    0.08
     DP
    0.08
     Iedere
    0.08
    िहार
    0.08
     Stir
    0.07
     staircase
    0.07
    Activations Density 0.003%

    No Known Activations