© 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. 3-RESID-POST-AA
    11. 1506
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ®,
    -0.08
     Neighborhood
    -0.08
    "id
    -0.08
    "profile
    -0.08
    ঢ়
    -0.08
     устра
    -0.08
     والم
    -0.08
     Akron
    -0.08
    ರೆ
    -0.07
     waiver
    -0.07
    POSITIVE LOGITS
    131
    0.07
    ación
    0.07
    Cook
    0.07
    Obj
    0.07
    atal
    0.07
     deduct
    0.07
    Sau
    0.07
    ng
    0.07
     ng
    0.06
    归
    0.06
    Activations Density 0.000%

    No Known Activations