© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 23-RESID-POST-AA
    11. 50156
    Prev
    Next
    INDEX
    Explanations

    comma

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laakiin
    -0.11
    but
    -0.11
    ですが
    -0.10
     imati
    -0.10
     ولكنه
    -0.10
     Бірақ
    -0.10
     but
    -0.09
     لكنه
    -0.09
     Однако
    -0.09
     you'd
    -0.09
    POSITIVE LOGITS
     помог
    0.10
     mình
    0.09
     я
    0.09
     nós
    0.09
     já
    0.09
     sudah
    0.09
     rád
    0.09
     så
    0.09
     мы
    0.09
     jestem
    0.08
    Activations Density 0.003%

    No Known Activations