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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110460
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raw
    -0.08
    element
    -0.07
    texto
    -0.07
    additional
    -0.07
     pict
    -0.07
    feature
    -0.07
    _cent
    -0.07
     Sum
    -0.07
     история
    -0.07
    slug
    -0.07
    POSITIVE LOGITS
    	callback
    0.13
    Callback
    0.12
    最终
    0.11
     callback
    0.11
    结束
    0.11
     callbacks
    0.11
    (callback
    0.11
    _callback
    0.11
    終了
    0.11
    Callbacks
    0.11
    Activations Density 0.005%

    No Known Activations