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. 90117
    Prev
    Next
    INDEX
    Explanations

    for

    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
    ikom
    -0.08
    емся
    -0.08
     investeren
    -0.08
    கம்
    -0.08
    ான்
    -0.08
    -largest
    -0.08
     έχουν
    -0.08
     Bla
    -0.08
    constructed
    -0.07
    ்வே
    -0.07
    POSITIVE LOGITS
     applicability
    0.09
    Applic
    0.09
    角色
    0.08
     synth
    0.07
    موضوع
    0.07
     chanson
    0.07
     toda
    0.07
     запрос
    0.07
     соглас
    0.07
     Applic
    0.07
    Activations Density 0.003%

    No Known Activations