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. 112844
    Prev
    Next
    INDEX
    Explanations

    letter of appreciation

    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
    .Mar
    -0.08
    (All
    -0.08
     asociaciones
    -0.08
    .mar
    -0.08
     použív
    -0.08
     kõik
    -0.08
    _mar
    -0.08
     inevitably
    -0.08
     shall
    -0.07
     választ
    -0.07
    POSITIVE LOGITS
     Helping
    0.10
     helping
    0.10
    Helping
    0.10
     kindness
    0.10
    帮助
    0.09
     helped
    0.09
    ساعد
    0.08
     помог
    0.08
     ayudarte
    0.08
     مساعد
    0.08
    Activations Density 0.028%

    No Known Activations