© 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. 19-RESID-POST-AA
    11. 18609
    Prev
    Next
    INDEX
    Explanations

    !

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     its
    -0.09
    。しかし
    -0.09
     serta
    -0.09
    .↵↵
    -0.09
     jedoch
    -0.09
    其
    -0.09
    。但是
    -0.08
    。此外
    -0.08
    。然而
    -0.08
     instance
    -0.08
    POSITIVE LOGITS
     �
    0.17
     I'm
    0.16
     I've
    0.14
    我是
    0.14
     �
    0.13
     أنا
    0.13
     I'd
    0.13
     저는
    0.13
     I
    0.12
     😊
    0.12
    Activations Density 0.015%

    No Known Activations