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. 43484
    Prev
    Next
    INDEX
    Explanations

    Reflection and mirrors

    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
    рап
    -0.09
     উদ্যোগ
    -0.08
     impactful
    -0.08
     genocide
    -0.08
     Serialization
    -0.08
     metabolism
    -0.08
     initiative
    -0.08
    асы
    -0.08
    امج
    -0.08
     هم
    -0.07
    POSITIVE LOGITS
     Shin
    0.08
    Avis
    0.08
    back
    0.08
     को
    0.08
    .stere
    0.07
     लगाने
    0.07
    .substring
    0.07
    ண்ண
    0.07
    ओ
    0.07
     परम
    0.07
    Activations Density 0.004%

    No Known Activations