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. 112875
    Prev
    Next
    INDEX
    Explanations

    commands

    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
    _ROM
    -0.08
     dout
    -0.08
    Ros
    -0.08
     海
    -0.08
     雅
    -0.08
    column
    -0.08
     crem
    -0.08
     miesz
    -0.08
     creamy
    -0.08
    wishlist
    -0.08
    POSITIVE LOGITS
     Reset
    0.08
     Inputs
    0.08
     Allowed
    0.07
     ایک
    0.07
    ہر
    0.07
    /team
    0.07
     allowed
    0.07
                                             
    0.07
     Redirect
    0.07
     conveying
    0.07
    Activations Density 0.000%

    No Known Activations