© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102374
    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'être
    -0.09
     surtout
    -0.09
    ്യക്ഷ
    -0.09
    'autres
    -0.09
     ailleurs
    -0.08
     wengine
    -0.08
    _FULLSCREEN
    -0.08
     കൂട്ട
    -0.08
     баҳ
    -0.08
    _SPEED
    -0.08
    POSITIVE LOGITS
     Example
    0.10
     Here
    0.10
     here
    0.09
     example
    0.09
     "./
    0.09
    จ
    0.09
     berupa
    0.09
     HERE
    0.09
    ??↵↵
    0.09
     выда
    0.09
    Activations Density 0.001%

    No Known Activations