© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 68727
    Prev
    Next
    INDEX
    Explanations

    code

    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
     threats
    -0.08
     bánh
    -0.07
     rand
    -0.07
     peper
    -0.07
     distractions
    -0.07
     confusion
    -0.07
     abs
    -0.07
     upcoming
    -0.07
     muita
    -0.07
    instead
    -0.07
    POSITIVE LOGITS
    .onclick
    0.08
    常委
    0.08
    .stop
    0.07
    .present
    0.07
    webtoken
    0.07
     Stops
    0.07
    .__
    0.07
    /scripts
    0.07
     tõttu
    0.07
     Swimming
    0.07
    Activations Density 0.006%

    No Known Activations