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. 12060
    Prev
    Next
    INDEX
    Explanations

    Apollo

    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
    ම්
    -0.08
    ging
    -0.08
     Facebook
    -0.08
    that's
    -0.07
    别人
    -0.07
    unc
    -0.07
     chute
    -0.07
    ાદ
    -0.07
    社会
    -0.07
    etime
    -0.07
    POSITIVE LOGITS
     laborator
    0.08
     विम
    0.08
     Sever
    0.08
     орган
    0.07
    Slot
    0.07
    Sto
    0.07
     gubern
    0.07
     Sua
    0.07
     решений
    0.07
    cupe
    0.07
    Activations Density 0.001%

    No Known Activations