© 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. 15-RESID-POST-AA
    11. 16723
    Prev
    Next
    INDEX
    Explanations

    say "everything/anything"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /script
    -0.08
    /runtime
    -0.08
     "./
    -0.07
    fa
    -0.07
    /dialog
    -0.07
     "`
    -0.07
    ?
↵
    -0.07
    _contract
    -0.07
     nekaj
    -0.07
    ?’
    -0.07
    POSITIVE LOGITS
     любых
    0.22
     любой
    0.21
     любые
    0.21
     любого
    0.21
     cualquier
    0.21
     любую
    0.20
     qualsiasi
    0.20
     любом
    0.20
     orice
    0.19
     enhver
    0.19
    Activations Density 0.045%

    No Known Activations