© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97234
    Prev
    Next
    INDEX
    Explanations

    PHP framework libraries

    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
    āina
    -0.09
    imam
    -0.08
    iedades
    -0.08
     صباح
    -0.08
     emir
    -0.08
     dang
    -0.08
     utu
    -0.08
    atsu
    -0.08
     mush
    -0.08
    étés
    -0.07
    POSITIVE LOGITS
    League
    0.16
     League
    0.15
     league
    0.15
     Symfony
    0.15
    league
    0.14
    Symfony
    0.12
     Swift
    0.12
     \
    0.12
     Rat
    0.12
    Swift
    0.11
    Activations Density 0.003%

    No Known Activations