Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43104
    Prev
    Next
    INDEX
    Explanations

    web communication

    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
    ونے
    -0.08
     وسط
    -0.08
     hechos
    -0.08
    ليب
    -0.07
    lama
    -0.07
    lywood
    -0.07
    ونا
    -0.07
    ہیں
    -0.07
     twenties
    -0.07
     vur
    -0.07
    POSITIVE LOGITS
    /null
    0.08
    Sug
    0.07
     valeur
    0.07
    不能为空
    0.07
    .null
    0.07
    /id
    0.07
    .progress
    0.07
    /mock
    0.07
     Sug
    0.07
     Barre
    0.07
    Activations Density 0.000%

    No Known Activations