© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29127
    Prev
    Next
    INDEX
    Explanations

    discussion

    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
     календар
    -0.10
     pudd
    -0.08
     Judas
    -0.08
     kalender
    -0.08
     tokenizer
    -0.08
     Quilt
    -0.08
    .Secret
    -0.08
    calendar
    -0.08
     beacon
    -0.07
    	Calendar
    -0.07
    POSITIVE LOGITS
    迅
    0.11
     hızlı
    0.11
     быстр
    0.11
     ઝડપી
    0.10
    即时
    0.10
     verbal
    0.10
     rapides
    0.10
     mabilis
    0.10
     articulate
    0.10
     rapide
    0.09
    Activations Density 0.014%

    No Known Activations