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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18913
    Prev
    Next
    INDEX
    Explanations

    testing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lied
    -0.08
     deductible
    -0.08
     hoofd
    -0.07
     oom
    -0.07
     Cartesian
    -0.07
     неоп
    -0.07
     উৎ
    -0.07
     প্রতি
    -0.07
    ierig
    -0.07
     disconnected
    -0.07
    POSITIVE LOGITS
     отзывы
    0.14
    反馈
    0.13
    _feedback
    0.13
    feedback
    0.12
    Feedback
    0.12
    liminary
    0.12
     auprès
    0.12
     Feedback
    0.11
     feedback
    0.11
     trials
    0.11
    Activations Density 0.017%

    No Known Activations