© 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. 103241
    Prev
    Next
    INDEX
    Explanations

    words with "z"

    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
    　第
    -0.09
    ','
    -0.08
     DISCLA
    -0.08
    ೊಂದ
    -0.08
    -Shirts
    -0.08
    /'
    -0.08
     personalised
    -0.08
    Battery
    -0.07
     dynamically
    -0.07
    -亚洲
    -0.07
    POSITIVE LOGITS
     z
    0.12
    "x
    0.11
    ,z
    0.11
    ξης
    0.10
     x
    0.10
    .z
    0.09
    ,x
    0.09
    .zz
    0.09
    xz
    0.09
    _x
    0.09
    Activations Density 0.056%

    No Known Activations