© 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. 7-RESID-POST-AA
    11. 1302
    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_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Milk
    -0.10
     Kan
    -0.09
    Swipe
    -0.08
    Kan
    -0.08
     Milk
    -0.08
     Yang
    -0.08
    redo
    -0.08
     Zid
    -0.08
    experiment
    -0.07
    .ma
    -0.07
    POSITIVE LOGITS
     incidents
    0.08
     réduire
    0.07
     RS
    0.07
    388
    0.07
     Valencia
    0.07
     voisin
    0.07
     simpl
    0.07
     váš
    0.07
     embarrassment
    0.07
     ತನ್ನ
    0.07
    Activations Density 0.044%

    No Known Activations