© 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. 19-RESID-POST-AA
    11. 103383
    Prev
    Next
    INDEX
    Explanations

    is

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ermöglicht
    -0.10
     erlaubt
    -0.09
     puissent
    -0.09
     puisse
    -0.09
     allowed
    -0.09
     permitido
    -0.09
     permitted
    -0.09
     gewünschten
    -0.09
    anceled
    -0.08
    合法
    -0.08
    POSITIVE LOGITS
     likely
    0.19
     probably
    0.18
     intriguing
    0.17
     quite
    0.17
     clearly
    0.17
     presumably
    0.17
     ambiguous
    0.17
     puzz
    0.16
    probably
    0.16
     provavelmente
    0.16
    Activations Density 0.048%

    No Known Activations