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

    Neuronpedia

    APICircuit 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. 75900
    Prev
    Next
    INDEX
    Explanations

    subject

    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
     Yang
    -0.08
     Sever
    -0.08
     Orientation
    -0.08
     이상의
    -0.08
    _orientation
    -0.08
     supp
    -0.07
     Orient
    -0.07
     diagon
    -0.07
    _diag
    -0.07
     Gay
    -0.07
    POSITIVE LOGITS
     enticing
    0.11
     catchy
    0.10
     crafted
    0.09
     वायरल
    0.09
     alluring
    0.09
     storefront
    0.08
    crafted
    0.08
    &utm
    0.08
    $mail
    0.08
     Crafted
    0.08
    Activations Density 0.002%

    No Known Activations