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. 120420
    Prev
    Next
    INDEX
    Explanations

    环

    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
     pooled
    -0.09
     kal
    -0.08
     �
    -0.08
     풀
    -0.08
     tunn
    -0.08
     hind
    -0.08
     ray
    -0.07
     confection
    -0.07
     squads
    -0.07
     dạng
    -0.07
    POSITIVE LOGITS
     whereby
    0.08
    起来
    0.08
    反馈
    0.08
    -feedback
    0.08
     Feedback
    0.08
     heated
    0.07
    ality
    0.07
    Feedback
    0.07
     Accountability
    0.07
     Heated
    0.07
    Activations Density 0.004%

    No Known Activations