© 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. 113314
    Prev
    Next
    INDEX
    Explanations

    default

    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
     destac
    -0.08
     Glück
    -0.08
     Orange
    -0.08
     sug
    -0.07
    énd
    -0.07
     contrasting
    -0.07
     eleg
    -0.07
    故
    -0.07
     хай
    -0.07
    iete
    -0.07
    POSITIVE LOGITS
     muut
    0.08
     zuwa
    0.08
    (Profile
    0.08
     Pdf
    0.08
     는
    0.08
    ছ
    0.08
     Rpc
    0.08
     아�
    0.08
    Pix
    0.08
     사항
    0.08
    Activations Density 0.003%

    No Known Activations