© 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. 47633
    Prev
    Next
    INDEX
    Explanations

    Foreign words for God

    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
     AS
    -0.08
     ==
    -0.08
     downtime
    -0.08
     yyyy
    -0.08
    201
    -0.08
     =
    -0.08
     let's
    -0.08
    ;
    -0.08
    		↵
    -0.08
    _it
    -0.08
    POSITIVE LOGITS
     ದೇವ
    0.14
     하나님
    0.14
     Hebrews
    0.14
     దేవ
    0.14
     divine
    0.13
     believers
    0.13
     ભગવાન
    0.12
     sinners
    0.12
     prophets
    0.12
     ঈ
    0.12
    Activations Density 0.123%

    No Known Activations