© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50050
    Prev
    Next
    INDEX
    Explanations

    Acronyms for organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Venue
    -0.09
    Venue
    -0.09
    Airport
    -0.08
    Environmental
    -0.08
     দিয়
    -0.08
     environmental
    -0.08
     Airport
    -0.08
     airport
    -0.08
     airplanes
    -0.08
     противоп
    -0.08
    POSITIVE LOGITS
     Whats
    0.09
    cale
    0.08
     rueda
    0.08
     एक
    0.08
     watan
    0.08
     Rowling
    0.08
     πρώτη
    0.08
    _desc
    0.07
     Linked
    0.07
     een
    0.07
    Activations Density 0.002%

    No Known Activations