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. 30446
    Prev
    Next
    INDEX
    Explanations

    Image generation prompts

    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
     lohnt
    -0.10
     oder
    -0.08
     eller
    -0.08
    -profit
    -0.08
     utawa
    -0.07
     victims
    -0.07
    _mar
    -0.07
     cyangwa
    -0.07
     Wissen
    -0.07
     atanapi
    -0.07
    POSITIVE LOGITS
     спаль
    0.08
     বাক
    0.08
    pụ
    0.08
     creativity
    0.07
    ะแ
    0.07
    @include
    0.07
    �
    0.07
     текст
    0.07
     disguise
    0.07
     تاکید
    0.07
    Activations Density 0.003%

    No Known Activations