© 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. 69199
    Prev
    Next
    INDEX
    Explanations

    to

    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
     stuff
    -0.11
     Stuff
    -0.10
    Stuff
    -0.08
     compuls
    -0.08
     ક્ર
    -0.08
    ेरी
    -0.08
     oppose
    -0.08
    _Exception
    -0.08
     negar
    -0.07
    stuff
    -0.07
    POSITIVE LOGITS
    上市
    0.10
     लॉन्च
    0.10
     срок
    0.09
     출시
    0.09
    нит
    0.08
     ಜಯ
    0.08
    emenangan
    0.08
     MVP
    0.08
     launched
    0.08
    ivité
    0.08
    Activations Density 0.004%

    No Known Activations