Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 131044
    Prev
    Next
    INDEX
    Explanations

    AN

    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
     distressed
    -0.09
     banks
    -0.09
     bank
    -0.08
     nap
    -0.08
     nub
    -0.07
     ബാങ്ക
    -0.07
     distress
    -0.07
     Banks
    -0.07
    Yr
    -0.07
     массов
    -0.07
    POSITIVE LOGITS
    (Mouse
    0.07
     Infiniti
    0.07
    _MENU
    0.07
    Quiet
    0.07
    时时
    0.07
     downstairs
    0.07
    _wifi
    0.07
    向
    0.07
     যাও
    0.07
    擊
    0.07
    Activations Density 0.001%

    No Known Activations