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. 129882
    Prev
    Next
    INDEX
    Explanations

    the

    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
    액
    -0.09
    ிற
    -0.08
    ำเภ
    -0.08
     ဝ
    -0.08
    یرہ
    -0.08
    เพิ่ม
    -0.08
    hetamine
    -0.08
    687
    -0.08
    ാക
    -0.08
    တ်
    -0.08
    POSITIVE LOGITS
     sana
    0.07
     bä
    0.07
     decomposition
    0.07
     hint
    0.07
     admiss
    0.07
    Initial
    0.07
     Initially
    0.07
    -valid
    0.07
     bubbly
    0.07
    _original
    0.07
    Activations Density 0.024%

    No Known Activations