© 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. 112727
    Prev
    Next
    INDEX
    Explanations

    x

    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
     Nachhalt
    -0.08
    exports
    -0.08
    ：https
    -0.07
     Yukon
    -0.07
    numer
    -0.07
    launch
    -0.07
     sostenible
    -0.07
    _updated
    -0.07
    setter
    -0.07
    akarta
    -0.07
    POSITIVE LOGITS
    003
    0.09
    536
    0.08
    252
    0.08
     psychiatr
    0.08
    494
    0.08
     beep
    0.08
    490
    0.08
    019
    0.08
    015
    0.08
    002
    0.08
    Activations Density 0.002%

    No Known Activations