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. 76374
    Prev
    Next
    INDEX
    Explanations

    Application development/UI frameworks

    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
    xton
    -0.08
    أكيد
    -0.08
    hoot
    -0.08
    -0.08
     ontwerpen
    -0.07
     featured
    -0.07
    Featured
    -0.07
    쓰기
    -0.07
    વાર
    -0.07
    imo
    -0.07
    POSITIVE LOGITS
     UIApplication
    0.09
    生命周期
    0.09
    .Single
    0.08
     Lifecycle
    0.08
    .support
    0.08
     Single
    0.08
    �
    0.07
    (Stage
    0.07
     interruptions
    0.07
     abrupt
    0.07
    Activations Density 0.003%

    No Known Activations