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. 43704
    Prev
    Next
    INDEX
    Explanations

    native

    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
    حه
    -0.10
     composé
    -0.08
    ингов
    -0.08
     الترك
    -0.08
     الإج
    -0.07
     compositions
    -0.07
    	em
    -0.07
    主体
    -0.07
    -compose
    -0.07
     compuesto
    -0.07
    POSITIVE LOGITS
    boots
    0.09
    voja
    0.08
     pride
    0.08
    uki
    0.08
     jednoduch
    0.08
    :G
    0.08
     zaka
    0.08
    izana
    0.08
    Asm
    0.07
     qaz
    0.07
    Activations Density 0.019%

    No Known Activations