© 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. 11-RESID-POST-AA
    11. 47362
    Prev
    Next
    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captive
    -0.09
     Synd
    -0.08
     Siam
    -0.08
    ैनिक
    -0.08
     tourist
    -0.08
     visitas
    -0.08
     maut
    -0.07
     Leben
    -0.07
     Mok
    -0.07
     Tribe
    -0.07
    POSITIVE LOGITS
    ;x
    0.09
     bowls
    0.08
    /x
    0.08
    xu
    0.08
    cepteur
    0.08
     ¶
    0.08
     flap
    0.08
     beams
    0.08
     recentes
    0.08
    #region
    0.08
    Activations Density 0.001%

    No Known Activations