© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64910
    Prev
    Next
    INDEX
    Explanations

    recycling and waste

    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
    zec
    -0.08
    突破
    -0.08
    々
    -0.08
     logr
    -0.07
    最高
    -0.07
     desafíos
    -0.07
    挑战
    -0.07
    kii
    -0.07
     bere
    -0.07
     Bere
    -0.07
    POSITIVE LOGITS
     дальней
    0.10
     fate
    0.10
     further
    0.10
     dalje
    0.10
    进一步
    0.09
     vidare
    0.09
    用途
    0.09
     деть
    0.09
     ued
    0.09
     назнач
    0.09
    Activations Density 0.078%

    No Known Activations