© 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. 45514
    Prev
    Next
    INDEX
    Explanations

    length

    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
    录
    -0.08
     Spirits
    -0.08
     Pants
    -0.08
     Powers
    -0.08
     Clem
    -0.07
     Win
    -0.07
    liner
    -0.07
     Ubuntu
    -0.07
     شر
    -0.07
     Linux
    -0.07
    POSITIVE LOGITS
     మంది
    0.10
    多少
    0.09
    ERE
    0.08
     fewer
    0.08
     antidepress
    0.08
     എണ്ണം
    0.08
    是多少
    0.08
    ையும்
    0.08
     kalor
    0.07
     betaal
    0.07
    Activations Density 0.009%

    No Known Activations