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. 97119
    Prev
    Next
    INDEX
    Explanations

    cl

    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
     quince
    -0.08
    šu
    -0.08
    ie
    -0.08
    ie's
    -0.08
    uwar
    -0.07
    ىسى
    -0.07
    iew
    -0.07
    indy
    -0.07
    rin
    -0.07
    onder
    -0.07
    POSITIVE LOGITS
    Adv
    0.09
     Zlat
    0.08
    adv
    0.08
    ad
    0.08
    AD
    0.08
    广告
    0.08
     هو
    0.08
     광고
    0.08
    広告
    0.08
     Advoc
    0.08
    Activations Density 0.000%

    No Known Activations