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. 15-RESID-POST-AA
    6. 19161
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     reportedly
    -0.10
     notoriously
    -0.09
    ന്നു
    -0.09
    jspb
    -0.09
    abes
    -0.09
    نامج
    -0.09
     prøve
    -0.09
    ัม
    -0.09
     zogenaamde
    -0.09
     вдруг
    -0.09
    POSITIVE LOGITS
     Discuss
    0.09
     discussed
    0.08
     Additionally
    0.08
    Discuss
    0.08
    GST
    0.08
     hierboven
    0.07
     Below
    0.07
     discuss
    0.07
     explained
    0.07
    ariance
    0.07
    Activations Density 0.017%

    No Known Activations