© 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. 8017
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WY
    -0.09
    terbury
    -0.08
     improper
    -0.08
     bodybuilding
    -0.08
     pengar
    -0.08
    keurig
    -0.08
    uud
    -0.08
    -single
    -0.08
    ikelihood
    -0.07
    translator
    -0.07
    POSITIVE LOGITS
     رنگ
    0.10
     lush
    0.10
     రంగ
    0.09
    色
    0.09
     色
    0.09
     lighting
    0.09
    clairage
    0.08
     നിറ
    0.08
     रंग
    0.08
    ähne
    0.08
    Activations Density 0.013%

    No Known Activations