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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47335
    Prev
    Next
    INDEX
    Explanations

    Winning

    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
    bild
    -0.09
    htub
    -0.08
    bilder
    -0.08
     Bild
    -0.07
    bak
    -0.07
    -rom
    -0.07
    -fiction
    -0.07
     Sofa
    -0.07
     TSA
    -0.07
    -air
    -0.07
    POSITIVE LOGITS
    此次
    0.09
     inicialmente
    0.09
     wannan
    0.09
    Markup
    0.08
    jenige
    0.08
     ağır
    0.08
    iket
    0.08
     aquesta
    0.08
     अधिकांश
    0.08
     reloc
    0.07
    Activations Density 0.024%

    No Known Activations