© 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. 23-RESID-POST-AA
    11. 49398
    Prev
    Next
    INDEX
    Explanations

    Divisibility and prime numbers

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     линия
    -0.08
    (-(
    -0.08
    浓
    -0.07
     aceler
    -0.07
    箭
    -0.07
     линии
    -0.07
     лини
    -0.07
    =-=-=-=-
    -0.07
     canvas
    -0.07
     graphics
    -0.07
    POSITIVE LOGITS
     divisible
    0.17
     integer
    0.16
    integer
    0.16
    prime
    0.15
     prime
    0.14
     divisor
    0.14
     divis
    0.14
    Prime
    0.14
    .integer
    0.14
     integers
    0.14
    Activations Density 0.168%

    No Known Activations