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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 120122
    Prev
    Next
    INDEX
    Explanations

    planting, ing

    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
     fals
    -0.08
    오는
    -0.08
     firmy
    -0.07
    cek
    -0.07
    ‌ని
    -0.07
     combin
    -0.07
     rynku
    -0.07
    ę
    -0.07
     merci
    -0.07
     redis
    -0.07
    POSITIVE LOGITS
     planting
    0.12
     ulang
    0.09
     મૂક
    0.09
     planted
    0.09
     વખતે
    0.08
    进去
    0.08
     recording
    0.08
     seedlings
    0.08
     seeds
    0.08
    出去
    0.08
    Activations Density 0.012%

    No Known Activations