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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44200
    Prev
    Next
    INDEX
    Explanations

    poverty and economy

    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
     vriendelijk
    -0.08
    ’ব
    -0.08
     것을
    -0.08
     Friend
    -0.08
     люблю
    -0.08
     sabía
    -0.08
    enal
    -0.07
     км
    -0.07
     aardig
    -0.07
    。截至
    -0.07
    POSITIVE LOGITS
     grievances
    0.13
     desperation
    0.11
     grievance
    0.10
     insufficient
    0.10
     inadequate
    0.10
     susceptibles
    0.09
     incentives
    0.09
     legitimate
    0.09
     vulnerable
    0.09
     despair
    0.09
    Activations Density 0.050%

    No Known Activations