Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130971
    Prev
    Next
    INDEX
    Explanations

    Sustainability/Iceland context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     çık
    -0.08
     August
    -0.08
     Iraqi
    -0.08
     AQU
    -0.08
     расшир
    -0.08
     Afrika
    -0.08
    .La
    -0.07
    庭
    -0.07
     çıx
    -0.07
     marchés
    -0.07
    POSITIVE LOGITS
     sh
    0.08
     shuffled
    0.08
    sho
    0.08
     shuffle
    0.08
     tsh
    0.07
     Shuffle
    0.07
     کری
    0.07
     Presidency
    0.07
     Splash
    0.07
     Rage
    0.07
    Activations Density 0.001%

    No Known Activations