© 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. 19-RESID-POST-AA
    11. 103225
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ones
    -0.08
    izations
    -0.08
     and
    -0.08
    ctions
    -0.08
    jections
    -0.08
     وغيرها
    -0.08
     prípade
    -0.07
     classiques
    -0.07
    ীদের
    -0.07
    inaries
    -0.07
    POSITIVE LOGITS
     irgendwie
    0.14
     Somehow
    0.14
     algún
    0.13
     irgend
    0.13
     somehow
    0.12
     algum
    0.12
     irgende
    0.11
     anderes
    0.11
     alguna
    0.11
     دیگری
    0.11
    Activations Density 0.057%

    No Known Activations