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. 130843
    Prev
    Next
    INDEX
    Explanations

    genetics/chromosomal abnormalities

    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
     amare
    -0.08
    itiba
    -0.08
     danych
    -0.08
    benza
    -0.08
     cookie
    -0.08
     mezelf
    -0.08
    粒
    -0.08
     البيانات
    -0.08
    meleri
    -0.08
    abta
    -0.07
    POSITIVE LOGITS
    junction
    0.08
    ోవ
    0.08
    Okay
    0.08
     part
    0.07
     Impression
    0.07
    Jo
    0.07
    599
    0.07
     Jo
    0.07
    Queries
    0.07
     מעבר
    0.07
    Activations Density 0.000%

    No Known Activations