Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43889
    Prev
    Next
    INDEX
    Explanations

    Software configuration settings

    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
    _walk
    -0.09
    精彩
    -0.08
     丰
    -0.08
     charity
    -0.08
    撮
    -0.08
     labore
    -0.08
     الله
    -0.08
     drones
    -0.07
     walk
    -0.07
    时时
    -0.07
    POSITIVE LOGITS
     controlling
    0.12
     настройки
    0.11
     togg
    0.10
     отключ
    0.10
     disables
    0.10
     disabling
    0.10
     влияет
    0.09
    .enabled
    0.09
    .Flags
    0.09
     Einstellung
    0.09
    Activations Density 0.018%

    No Known Activations