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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 111797
    Prev
    Next
    INDEX
    Explanations

    self-improvement advice

    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
    }}},↵
    -0.08
    Withdraw
    -0.07
    _ack
    -0.07
    Further
    -0.07
     Александр
    -0.07
     таки
    -0.07
    Dv
    -0.07
    Amount
    -0.07
     പിന്നീട്
    -0.07
    ankar
    -0.07
    POSITIVE LOGITS
     wellness
    0.11
     kesehatan
    0.11
     Wellness
    0.10
    幸福
    0.10
     здоровье
    0.10
     sculpt
    0.10
     santé
    0.09
     здоровья
    0.09
     ఆరో
    0.09
    -health
    0.09
    Activations Density 0.028%

    No Known Activations