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. 106145
    Prev
    Next
    INDEX
    Explanations

    data storage technologies

    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
     prosec
    -0.10
     hostility
    -0.09
     جوان
    -0.09
     Emin
    -0.09
     Coke
    -0.09
     التجارة
    -0.08
     spullen
    -0.08
     police
    -0.08
    	lock
    -0.08
     documenting
    -0.08
    POSITIVE LOGITS
    .remote
    0.08
     Bly
    0.08
     உருவ
    0.07
     bridging
    0.07
    qh
    0.07
     மேற்க
    0.07
     feit
    0.07
    �
    0.07
     metastatic
    0.07
     Hotel
    0.07
    Activations Density 0.006%

    No Known Activations