© 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. 30347
    Prev
    Next
    INDEX
    Explanations

    Where

    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
     hela
    -0.08
     Compet
    -0.08
     competencia
    -0.08
     Starting
    -0.07
     Lost
    -0.07
    Compet
    -0.07
     querido
    -0.07
     Rus
    -0.07
    Sim
    -0.07
    ину
    -0.07
    POSITIVE LOGITS
     qualifies
    0.09
     philosoph
    0.08
    waż
    0.08
    ற்ப
    0.08
    _candidates
    0.08
    (!(
    0.08
    xp
    0.08
     brave
    0.07
    услов
    0.07
    Trash
    0.07
    Activations Density 0.002%

    No Known Activations