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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 97110
    Prev
    Next
    INDEX
    Explanations

    say left

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _VERTICAL
    -0.09
    コピー
    -0.09
     copying
    -0.09
     headings
    -0.09
     copy
    -0.09
     Messi
    -0.08
     verticale
    -0.08
    	copy
    -0.08
    Copy
    -0.08
     copia
    -0.08
    POSITIVE LOGITS
     flush
    0.20
     flushed
    0.19
     Flush
    0.19
    flush
    0.19
    Flush
    0.18
    _flush
    0.15
    .flush
    0.15
     flushing
    0.14
    .Flush
    0.12
     अल
    0.10
    Activations Density 0.005%

    No Known Activations