© 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. 68413
    Prev
    Next
    INDEX
    Explanations

    with

    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
     Constitu
    -0.09
     imo
    -0.08
    atioun
    -0.08
    /include
    -0.08
    	Double
    -0.08
     기본
    -0.08
    _scal
    -0.08
     [%
    -0.07
    (GTK
    -0.07
    (Optional
    -0.07
    POSITIVE LOGITS
     protagonist
    0.13
     narrator
    0.12
     poign
    0.11
     poignant
    0.10
     protagonista
    0.09
     recount
    0.09
    主人
    0.09
     happenings
    0.09
     restless
    0.09
     heroine
    0.09
    Activations Density 0.065%

    No Known Activations