© 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. 68563
    Prev
    Next
    INDEX
    Explanations

    alternatives

    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
    出了
    -0.08
     Frances
    -0.08
     textbook
    -0.08
     Mestre
    -0.08
    婦
    -0.08
    正确
    -0.07
     موجود
    -0.07
     domést
    -0.07
     turística
    -0.07
    要求
    -0.07
    POSITIVE LOGITS
    Proposal
    0.09
     propose
    0.09
     voorstel
    0.09
     Proposal
    0.08
     proposing
    0.08
     proposal
    0.08
     proposes
    0.08
    Official
    0.08
     कल्प
    0.08
     combinations
    0.07
    Activations Density 0.025%

    No Known Activations