© 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. 91446
    Prev
    Next
    INDEX
    Explanations

    chatbots and NLP

    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
    取消
    -0.09
     gast
    -0.07
     patch
    -0.07
    iyor
    -0.07
     penalty
    -0.07
     pén
    -0.07
    Tenant
    -0.07
     proposal
    -0.07
     suspected
    -0.07
     penalties
    -0.07
    POSITIVE LOGITS
     sayings
    0.13
     jokes
    0.12
    Replies
    0.10
     encycl
    0.10
     amusing
    0.10
     humorous
    0.10
     философ
    0.10
     clueless
    0.10
     frases
    0.10
    百科
    0.10
    Activations Density 0.004%

    No Known Activations