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. 11-RESID-POST-AA
    6. 60783
    Prev
    Next
    INDEX
    Explanations

    international relations

    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
     кредит
    -0.09
     dishwasher
    -0.08
    Sunny
    -0.08
    ugar
    -0.07
    Atr
    -0.07
     Pussy
    -0.07
    ുസ
    -0.07
     депозит
    -0.07
     thankful
    -0.07
     цилинд
    -0.07
    POSITIVE LOGITS
    双方
    0.14
     birbir
    0.11
     બંને
    0.10
     diplomats
    0.10
     વચ્ચે
    0.09
    之间
    0.09
     ambos
    0.09
     vone
    0.09
     दोनों
    0.09
     વચ્ચ
    0.09
    Activations Density 0.060%

    No Known Activations