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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119249
    Prev
    Next
    INDEX
    Explanations

    educational institutions

    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
     churn
    -0.09
     रिलीज
    -0.08
    รว
    -0.08
     crossover
    -0.08
    atég
    -0.08
     contag
    -0.08
    เกิด
    -0.08
    क्राउ
    -0.08
    _nf
    -0.07
    cią
    -0.07
    POSITIVE LOGITS
    Authority
    0.09
    Har
    0.08
     authorities
    0.08
    authority
    0.08
     Progn
    0.08
    achim
    0.08
     authority
    0.08
    International
    0.08
    Selective
    0.08
     ведущ
    0.08
    Activations Density 0.027%

    No Known Activations