© 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. 23-RESID-POST-AA
    11. 49255
    Prev
    Next
    INDEX
    Explanations

    GPT

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SVN
    -0.11
     svn
    -0.11
    FXML
    -0.10
    .xls
    -0.10
    bower
    -0.10
    PHPExcel
    -0.10
    @Find
    -0.09
     WWF
    -0.09
    svn
    -0.09
     ftp
    -0.09
    POSITIVE LOGITS
    <|start|>
    0.21
    _chat
    0.20
     GPT
    0.19
    .chat
    0.19
    (prompt
    0.18
    .Chat
    0.18
    <|end|>
    0.18
    Chat
    0.18
     chat
    0.18
    _prompt
    0.17
    Activations Density 0.027%

    No Known Activations