© 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. 103544
    Prev
    Next
    INDEX
    Explanations

    display and interfaces

    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
     persunas
    -0.09
     tsev
    -0.08
    cesz
    -0.08
    ोक
    -0.08
    ioù
    -0.08
    ڪار
    -0.08
    zbollah
    -0.08
    纪委
    -0.08
    199
    -0.08
    ֿ
    -0.08
    POSITIVE LOGITS
    :none
    0.11
    :inline
    0.11
    :flex
    0.10
    (Name
    0.09
    Name
    0.09
    able
    0.09
    ational
    0.09
    atively
    0.08
    :block
    0.08
     nowrap
    0.08
    Activations Density 0.013%

    No Known Activations