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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 54062
    Prev
    Next
    INDEX
    Explanations

    if

    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
     unexpectedly
    -0.08
     Lle
    -0.07
    晰
    -0.07
    しょう
    -0.07
    .handle
    -0.07
    references
    -0.07
    েলা
    -0.07
    abilecek
    -0.07
     Possible
    -0.07
    lofen
    -0.07
    POSITIVE LOGITS
     సంఘ
    0.09
    仅
    0.08
    කා
    0.08
     opr
    0.08
     சம்ப
    0.08
     eher
    0.08
     prefer
    0.08
     prefers
    0.08
    طالب
    0.08
     ઘટના
    0.08
    Activations Density 0.018%

    No Known Activations