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. 102721
    Prev
    Next
    INDEX
    Explanations

    dashes

    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
     uw
    -0.07
    <context
    -0.07
    >>↵↵
    -0.07
    uler
    -0.07
     conj
    -0.07
    -course
    -0.07
     combining
    -0.07
    CU
    -0.07
     deploying
    -0.07
    .g
    -0.07
    POSITIVE LOGITS
     ні
    0.09
     الاتفاق
    0.09
     tois
    0.08
     Neck
    0.08
     المعارضة
    0.08
     প্রাণ
    0.08
     الهي
    0.08
     غير
    0.08
     komin
    0.08
     কা�
    0.08
    Activations Density 0.012%

    No Known Activations