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

    Neuronpedia

    Jacobian LensNEW
    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. 112630
    Prev
    Next
    INDEX
    Explanations

    divisibility of numbers

    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
     cabin
    -0.09
    _COUNTER
    -0.08
     onboard
    -0.08
    -Bahn
    -0.08
    (Register
    -0.08
     rallies
    -0.08
    线路
    -0.08
    (register
    -0.08
    -call
    -0.08
     frontage
    -0.08
    POSITIVE LOGITS
     hierarchical
    0.11
    Ancestor
    0.11
     ancestor
    0.11
     Hier
    0.10
    ancestor
    0.10
    hier
    0.10
    Hier
    0.10
    Hierarchy
    0.09
     downgrade
    0.09
     Anc
    0.09
    Activations Density 0.013%

    No Known Activations