© 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. 110522
    Prev
    Next
    INDEX
    Explanations

    Global Interpreter Lock (GIL)

    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
    URU
    -0.09
    -sav
    -0.08
    :=
    -0.08
    uro
    -0.08
     UR
    -0.07
     urb
    -0.07
     किश
    -0.07
     숙
    -0.07
    decorate
    -0.07
    _U
    -0.07
    POSITIVE LOGITS
     limitations
    0.11
     limitation
    0.11
    limitations
    0.09
     Heap
    0.08
    Heap
    0.08
    限制
    0.08
     concurrency
    0.08
    agrada
    0.08
     limita
    0.08
     caretaker
    0.08
    Activations Density 0.001%

    No Known Activations