© 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. 54531
    Prev
    Next
    INDEX
    Explanations

    words

    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
     Pessoa
    -0.08
     guards
    -0.07
    elas
    -0.07
    blur
    -0.07
    clazz
    -0.07
    cus
    -0.07
    bord
    -0.07
    aver
    -0.07
    /check
    -0.07
     Zimbabwe
    -0.07
    POSITIVE LOGITS
    组成
    0.09
    igh
    0.08
     भुगतान
    0.08
     pochi
    0.08
    hnya
    0.08
    Мы
    0.08
    У
    0.08
     özel
    0.08
     firma
    0.08
    とも
    0.08
    Activations Density 0.008%

    No Known Activations