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. 43321
    Prev
    Next
    INDEX
    Explanations

    :

    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
     Nantes
    -0.08
    Mux
    -0.08
     Sah
    -0.08
     solt
    -0.07
     dissent
    -0.07
    .nc
    -0.07
    ory
    -0.07
    時間
    -0.07
     परिव
    -0.07
    XM
    -0.07
    POSITIVE LOGITS
     utilizes
    0.08
     inhoud
    0.08
    :中国
    0.08
     affaires
    0.07
    hair
    0.07
    	In
    0.07
     enzym
    0.07
     enzyme
    0.07
    ánh
    0.07
     électroniques
    0.07
    Activations Density 0.003%

    No Known Activations