© 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. 19-RESID-POST-AA
    11. 102270
    Prev
    Next
    INDEX
    Explanations

    Divisibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Convert
    -0.08
     WWW
    -0.08
    Convert
    -0.07
     Tokyo
    -0.07
     reconstruct
    -0.07
     scientific
    -0.07
     Combine
    -0.07
     cognitive
    -0.07
    WWW
    -0.07
     zou
    -0.07
    POSITIVE LOGITS
     divisible
    0.20
     divis
    0.16
     divisor
    0.14
     división
    0.12
     divides
    0.12
     divisão
    0.12
     multiples
    0.11
    /div
    0.11
    div
    0.11
     dividing
    0.11
    Activations Density 0.034%

    No Known Activations