© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44420
    Prev
    Next
    INDEX
    Explanations

    but

    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
     meeste
    -0.08
    Summ
    -0.08
    当然
    -0.08
    summ
    -0.08
    -0.07
    ес
    -0.07
    (t
    -0.07
     BD
    -0.07
     summar
    -0.07
    fø
    -0.07
    POSITIVE LOGITS
     también
    0.09
     juga
    0.09
     उससे
    0.09
     eur
    0.09
     всей
    0.09
     tambien
    0.08
     etiam
    0.08
    También
    0.08
     também
    0.08
     tamén
    0.08
    Activations Density 0.052%
    No Known Activations