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. 12147
    Prev
    Next
    INDEX
    Explanations

    data recovery

    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
    decor
    -0.09
     dislikes
    -0.09
     Cupid
    -0.08
     décoration
    -0.08
     wang
    -0.08
     CAPITAL
    -0.08
     keuntungan
    -0.08
     laj
    -0.08
     chords
    -0.08
     axle
    -0.08
    POSITIVE LOGITS
     reconstruct
    0.14
     reconstruction
    0.12
    .restore
    0.12
     Reconstruction
    0.11
     reconstructed
    0.11
     restoring
    0.10
    	restore
    0.10
     Restore
    0.10
     восстановления
    0.10
    恢复
    0.09
    Activations Density 0.008%

    No Known Activations