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. 53264
    Prev
    Next
    INDEX
    Explanations

    x

    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
    .zip
    -0.08
     natürliche
    -0.08
     pastors
    -0.07
     Travel
    -0.07
     sump
    -0.07
     Monthly
    -0.07
     zipped
    -0.07
     sealing
    -0.07
     Transmission
    -0.07
    כר
    -0.07
    POSITIVE LOGITS
     jolla
    0.07
     মূল্য
    0.07
    (answer
    0.07
    Equals
    0.07
     هم
    0.07
    uchsia
    0.07
    Requires
    0.07
    Raise
    0.07
    *u
    0.07
    ്വേഷ
    0.07
    Activations Density 0.029%

    No Known Activations