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. 568
    Prev
    Next
    INDEX
    Explanations

    index

    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
    aval
    -0.08
    -access
    -0.08
     gird
    -0.08
    োনা
    -0.08
    вается
    -0.07
    -0.07
     avion
    -0.07
    _PROP
    -0.07
     dioc
    -0.07
    .theta
    -0.07
    POSITIVE LOGITS
     fasting
    0.08
    ury
    0.08
     Kip
    0.08
     cruel
    0.08
     rehabil
    0.08
    低
    0.08
    巧
    0.07
     cruelty
    0.07
     انخفاض
    0.07
     {!!
    0.07
    Activations Density 0.001%

    No Known Activations