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. 67224
    Prev
    Next
    INDEX
    Explanations

    Depression/Loss of interest

    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
     देशों
    -0.09
     Maps
    -0.08
     megap
    -0.08
     Specify
    -0.08
     हस्त
    -0.08
     civilizations
    -0.07
     Unsupported
    -0.07
     Mali
    -0.07
     Comparable
    -0.07
     Map
    -0.07
    POSITIVE LOGITS
     depression
    0.11
     depressive
    0.10
     Depression
    0.10
     depressed
    0.09
     anos
    0.09
     ಉತ್ಪ
    0.09
     demean
    0.08
     تغيير
    0.08
     despair
    0.08
     antidepress
    0.08
    Activations Density 0.022%

    No Known Activations