© 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. 24618
    Prev
    Next
    INDEX
    Explanations

    congratulating

    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
    .intent
    -0.08
     केला
    -0.08
    split
    -0.08
    Really
    -0.07
    ))/(
    -0.07
     helmet
    -0.07
    _split
    -0.07
     החלט
    -0.07
    (filepath
    -0.07
     intending
    -0.07
    POSITIVE LOGITS
    åd
    0.09
     Anders
    0.08
     tüm
    0.08
     neka
    0.08
     richtet
    0.08
     Selection
    0.08
     Sele
    0.08
     koji
    0.08
     Balt
    0.08
     ayrıca
    0.08
    Activations Density 0.017%

    No Known Activations