© 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. 15-RESID-POST-AA
    11. 16677
    Prev
    Next
    INDEX
    Explanations

    gibberish texts

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notation
    -0.08
    (parent
    -0.08
     convenient
    -0.08
     that
    -0.08
     for
    -0.08
    ง่าย
    -0.08
    ;
    -0.07
    's
    -0.07
     сначала
    -0.07
     enger
    -0.07
    POSITIVE LOGITS
     lectores
    0.09
    348
    0.09
     leitores
    0.08
    Celebrate
    0.08
    ਠ
    0.08
    AIza
    0.08
    Bad
    0.08
     Affero
    0.08
    zanp
    0.08
    Lorem
    0.08
    Activations Density 0.086%

    No Known Activations