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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103037
    Prev
    Next
    INDEX
    Explanations

    words or characters

    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
     COMPLETE
    -0.09
     herhangi
    -0.09
    isição
    -0.08
    _UNKNOWN
    -0.08
     אך
    -0.08
     USING
    -0.08
     allerdings
    -0.08
    _NOT
    -0.08
    .lib
    -0.07
    _not
    -0.07
    POSITIVE LOGITS
     constitutes
    0.11
     per
    0.10
     பகுத
    0.09
     to
    0.09
     constitute
    0.09
    正文
    0.08
    ərlər
    0.08
    enski
    0.08
    ంటే
    0.08
     paragraphs
    0.08
    Activations Density 0.008%

    No Known Activations