© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30268
    Prev
    Next
    INDEX
    Explanations

    loops in programming

    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
     agli
    -0.08
     espec
    -0.08
     cadas
    -0.08
     positions
    -0.07
     cocoa
    -0.07
     edificios
    -0.07
    ynthesize
    -0.07
     buildings
    -0.07
     भाव
    -0.07
     occasion
    -0.07
    POSITIVE LOGITS
    _until
    0.12
     termination
    0.12
    Termination
    0.11
    termination
    0.11
    退出
    0.11
     exited
    0.11
    .until
    0.10
     loop
    0.10
    until
    0.10
     loops
    0.10
    Activations Density 0.010%

    No Known Activations