© 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. 7-RESID-POST-AA
    11. 1513
    Prev
    Next
    INDEX
    Explanations

    node

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     δ
    -0.08
     patents
    -0.08
    Programm
    -0.08
    atsby
    -0.07
     oste
    -0.07
     alış
    -0.07
     Telerik
    -0.07
     arterial
    -0.07
    MW
    -0.07
    ifact
    -0.07
    POSITIVE LOGITS
    -era
    0.09
     benefici
    0.08
     Suspension
    0.07
     cuisine
    0.07
    \Carbon
    0.07
     ecos
    0.07
     Beer
    0.07
     keuken
    0.07
    �
    0.07
     suspended
    0.07
    Activations Density 0.003%

    No Known Activations