© 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. 11-RESID-POST-AA
    11. 69431
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     mace
    -0.09
     Neust
    -0.08
     Certified
    -0.08
     Neptune
    -0.08
    명을
    -0.08
     princes
    -0.08
     Cinderella
    -0.08
     rnd
    -0.08
    명이
    -0.08
     Citation
    -0.08
    POSITIVE LOGITS
     ramp
    0.09
    一样
    0.08
     beneficiary
    0.08
    房地产
    0.07
    <Auth
    0.07
    والی
    0.07
     technically
    0.07
     asym
    0.07
     rightly
    0.07
    imeters
    0.07
    Activations Density 0.142%

    No Known Activations