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. 106104
    Prev
    Next
    INDEX
    Explanations

    walking

    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
     eth
    -0.08
     дер
    -0.08
     директор
    -0.08
     hår
    -0.07
     ஆ
    -0.07
     பாட
    -0.07
     சென்ற
    -0.07
     قرار
    -0.07
     бл
    -0.07
     மூ
    -0.07
    POSITIVE LOGITS
     paced
    0.10
    -paced
    0.09
    ثق
    0.08
     calories
    0.08
    促进
    0.08
    /gr
    0.08
    ෙන්
    0.08
     Counseling
    0.08
    forecast
    0.08
     ekstra
    0.08
    Activations Density 0.006%

    No Known Activations