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. 77243
    Prev
    Next
    INDEX
    Explanations

    Coffee/lattes

    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
     période
    -0.08
    EXIT
    -0.08
    ��
    -0.07
    -European
    -0.07
    ���
    -0.07
    ����
    -0.07
    ONE
    -0.07
    го
    -0.07
    耳
    -0.07
    .Primary
    -0.07
    POSITIVE LOGITS
     layers
    0.11
     layered
    0.11
     capas
    0.11
     overlays
    0.10
    overlay
    0.10
     layering
    0.09
    Layers
    0.09
     �
    0.09
    _layers
    0.09
     overlay
    0.09
    Activations Density 0.016%

    No Known Activations