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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 44780
    Prev
    Next
    INDEX
    Explanations

    modular arithmetic

    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
     trips
    -0.09
    Movies
    -0.08
     measure
    -0.08
    (Rect
    -0.07
     drawbacks
    -0.07
    eting
    -0.07
    Pricing
    -0.07
     movies
    -0.07
    Trips
    -0.07
     Measure
    -0.07
    POSITIVE LOGITS
     congr
    0.11
    -solving
    0.10
     Caesar
    0.10
    Modulo
    0.10
     modulo
    0.10
    Solve
    0.09
     solv
    0.09
     Solve
    0.09
    .solve
    0.09
     remainder
    0.09
    Activations Density 0.022%

    No Known Activations