© 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. 16367
    Prev
    Next
    INDEX
    Explanations

    Chatbot system messages

    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
    _aut
    -0.07
     Universal
    -0.07
     Uni
    -0.07
     إجراءات
    -0.07
     Automated
    -0.07
    enzi
    -0.07
    环球
    -0.07
    izar
    -0.07
    社会
    -0.07
     Bib
    -0.07
    POSITIVE LOGITS
     среднего
    0.10
     чыг
    0.09
     familias
    0.09
     પહેલાં
    0.09
     öň
    0.09
    .randn
    0.08
     перад
    0.08
    راه
    0.08
    ’avant
    0.08
    grund
    0.08
    Activations Density 0.073%

    No Known Activations