© 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. 16433
    Prev
    Next
    INDEX
    Explanations

    vector

    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
     prohibits
    -0.08
     promotes
    -0.08
    population
    -0.08
    .gener
    -0.08
     population
    -0.08
     tantal
    -0.08
     naše
    -0.07
     conducts
    -0.07
     strengthens
    -0.07
     begins
    -0.07
    POSITIVE LOGITS
     qualit
    0.11
     qualitative
    0.11
     kwalitat
    0.09
     qualitat
    0.09
     Qual
    0.09
     Loyalty
    0.08
     الفني
    0.08
     Loki
    0.08
     Structural
    0.08
    qual
    0.08
    Activations Density 0.136%

    No Known Activations