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. 130785
    Prev
    Next
    INDEX
    Explanations

    variations of Г

    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
     krij
    -0.08
    ating
    -0.08
    hell
    -0.07
     мен
    -0.07
    kin
    -0.07
     resemblance
    -0.07
     Oxford
    -0.07
    ksen
    -0.07
    _reverse
    -0.07
     transpar
    -0.07
    POSITIVE LOGITS
    инек
    0.09
    ર્ભ
    0.09
    erms
    0.09
    енные
    0.09
    erm
    0.09
    ರ್ಭ
    0.09
    ıda
    0.08
    ాయం
    0.08
    ной
    0.08
    ermin
    0.08
    Activations Density 0.010%

    No Known Activations