© 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. 810
    Prev
    Next
    INDEX
    Explanations

    added

    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
    一本
    -0.08
    MEM
    -0.08
     principios
    -0.07
    스템
    -0.07
     sauf
    -0.07
    திர
    -0.07
     nave
    -0.07
     hypot
    -0.07
     flu
    -0.07
    Rec
    -0.07
    POSITIVE LOGITS
    յալ
    0.08
     killings
    0.08
    	before
    0.07
     없이
    0.07
     Fähigkeiten
    0.07
     DIGITAL
    0.07
     യുവ
    0.07
    -Aus
    0.07
    iði
    0.07
     ಯುವ
    0.07
    Activations Density 0.003%

    No Known Activations