© 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. 108220
    Prev
    Next
    INDEX
    Explanations

    7 and 9

    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
     prowess
    -0.07
    主动
    -0.07
     entorno
    -0.07
    folk
    -0.07
    ایی
    -0.07
     brou
    -0.07
     hâ
    -0.07
    .infinity
    -0.07
    jego
    -0.07
     Einstellungen
    -0.07
    POSITIVE LOGITS
     аналог
    0.07
     anual
    0.07
     IO
    0.07
     grew
    0.07
    Animate
    0.07
    ganos
    0.07
     друз
    0.07
    Myst
    0.07
     Scroll
    0.07
    구
    0.07
    Activations Density 0.001%

    No Known Activations