© 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. 95077
    Prev
    Next
    INDEX
    Explanations

    _mode

    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
     कैसी
    -0.08
     WAN
    -0.08
     diss
    -0.08
     unplug
    -0.08
     Är
    -0.08
    .dataset
    -0.08
    ښ
    -0.08
    คล
    -0.08
     dissip
    -0.08
    λών
    -0.07
    POSITIVE LOGITS
    496
    0.08
     enum
    0.08
    枚
    0.08
    enum
    0.08
     Enumeration
    0.08
    Enum
    0.08
    Convention
    0.08
     Montreal
    0.08
    Formatting
    0.08
    Christmas
    0.07
    Activations Density 0.001%

    No Known Activations