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. 23-RESID-POST-AA
    6. 130753
    Prev
    Next
    INDEX
    Explanations

    and

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ben
    -0.09
    words
    -0.08
     samt
    -0.08
    бав
    -0.08
    att
    -0.08
    альян
    -0.08
    elwe
    -0.07
    -att
    -0.07
     uttry
    -0.07
     mn
    -0.07
    POSITIVE LOGITS
     prejudice
    0.12
     Pre
    0.10
     preju
    0.09
     Place
    0.09
    <(),
    0.09
     Necess
    0.09
    _Instance
    0.08
    _Pre
    0.08
     Profile
    0.08
    judice
    0.08
    Activations Density 0.002%

    No Known Activations