© 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. 96574
    Prev
    Next
    INDEX
    Explanations

    metadata and data catalogs

    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
    ิต
    -0.10
    .COMP
    -0.09
    anning
    -0.08
    āti
    -0.08
     citizenship
    -0.08
    _credentials
    -0.08
    arii
    -0.08
    .credentials
    -0.08
    애
    -0.08
     став
    -0.08
    POSITIVE LOGITS
     rekord
    0.10
     Whois
    0.09
     Dublin
    0.09
     Music
    0.09
     er
    0.08
     Er
    0.08
     FR
    0.08
     konse
    0.08
     Pool
    0.08
     CK
    0.08
    Activations Density 0.001%

    No Known Activations