© 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. 12778
    Prev
    Next
    INDEX
    Explanations

    �

    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
    軍
    -0.10
    650
    -0.08
    neal
    -0.08
    ines
    -0.08
     ней
    -0.08
    军
    -0.07
     realms
    -0.07
     направления
    -0.07
     направ
    -0.07
     militares
    -0.07
    POSITIVE LOGITS
    buddy
    0.08
    Ball
    0.07
     adjusts
    0.07
    pz
    0.07
     అంట
    0.07
    बल
    0.07
    Scoped
    0.07
    mien
    0.07
     asal
    0.07
     fraternity
    0.07
    Activations Density 0.000%

    No Known Activations