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. 44045
    Prev
    Next
    INDEX
    Explanations

    Interference

    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
    迎
    -0.08
     бағдарлам
    -0.07
     програм
    -0.07
     program
    -0.07
     couch
    -0.07
     particular
    -0.07
    árm
    -0.07
     Palo
    -0.07
     bancos
    -0.07
    dated
    -0.07
    POSITIVE LOGITS
     sabotage
    0.11
     harassment
    0.10
     हमला
    0.10
    _proxy
    0.09
     wreak
    0.09
     retali
    0.09
     вмеш
    0.08
     دفاع
    0.08
     retaliation
    0.08
     Favorites
    0.08
    Activations Density 0.010%

    No Known Activations