© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44562
    Prev
    Next
    INDEX
    Explanations

    erd

    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
     Jim
    -0.08
     allow
    -0.08
     rays
    -0.07
    _level
    -0.07
     plates
    -0.07
    _LEVEL
    -0.07
     jawa
    -0.07
     representatives
    -0.07
    olders
    -0.07
     OB
    -0.07
    POSITIVE LOGITS
    -election
    0.08
    .Stock
    0.08
    Election
    0.08
    facebook
    0.08
     election
    0.08
    Fleet
    0.08
    Hosted
    0.08
    Scatter
    0.08
     alkalmaz
    0.07
    小游戏
    0.07
    Activations Density 0.000%

    No Known Activations