© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29471
    Prev
    Next
    INDEX
    Explanations

    Say

    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
     puls
    -0.08
     wunder
    -0.08
     hank
    -0.07
     conquered
    -0.07
    కం
    -0.07
    ువు
    -0.07
     verv
    -0.07
     rd
    -0.07
    ampp
    -0.07
    angu
    -0.07
    POSITIVE LOGITS
     बातचीत
    0.10
     conversaciones
    0.09
     Gespräch
    0.09
    ------------------------------------------------------------------------------
    0.09
     //</
    0.09
     gesprek
    0.09
    обр
    0.08
     sohbet
    0.08
     сөйл
    0.08
     exchanged
    0.08
    Activations Density 0.034%

    No Known Activations