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. 111844
    Prev
    Next
    INDEX
    Explanations

    recommended

    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
     pasado
    -0.09
    ע
    -0.08
    _HAS
    -0.07
    Was
    -0.07
    165
    -0.07
    �
    -0.07
     принимает
    -0.07
     прошл
    -0.07
     Wants
    -0.07
    -vector
    -0.07
    POSITIVE LOGITS
     vivement
    0.12
     사항
    0.10
    사항
    0.09
    事項
    0.09
     recommended
    0.09
    函
    0.09
     Operating
    0.09
     fortement
    0.08
     Judy
    0.08
     sincerely
    0.08
    Activations Density 0.023%

    No Known Activations