© 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. 14
    Prev
    Next
    INDEX
    Explanations

    以

    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
     जैसी
    -0.08
     maintain
    -0.08
     Warcraft
    -0.08
    -maint
    -0.07
     antre
    -0.07
    Maint
    -0.07
     incend
    -0.07
    警
    -0.07
    artos
    -0.07
    局
    -0.07
    POSITIVE LOGITS
     przypadku
    0.09
    (pid
    0.09
     grinders
    0.08
    (api
    0.08
     dubb
    0.08
    rico
    0.08
    一下
    0.08
     Extra
    0.08
    (common
    0.08
    ichtigkeit
    0.07
    Activations Density 0.006%

    No Known Activations