© 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. 7703
    Prev
    Next
    INDEX
    Explanations

    use

    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
    .typ
    -0.08
     crafty
    -0.08
    quelle
    -0.08
    icherheit
    -0.08
     টাই
    -0.08
    icals
    -0.08
    ytics
    -0.07
     横
    -0.07
    ър
    -0.07
    gments
    -0.07
    POSITIVE LOGITS
     trabajador
    0.08
     بعيد
    0.08
     dano
    0.08
     distracting
    0.08
    മായ
    0.08
     والتر
    0.08
     لأ
    0.08
     Mano
    0.08
     €
    0.08
     لجميع
    0.08
    Activations Density 0.002%

    No Known Activations