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. 11635
    Prev
    Next
    INDEX
    Explanations

    sorry

    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
     MRI
    -0.08
     borr
    -0.07
     delegate
    -0.07
     facture
    -0.07
     clubhouse
    -0.07
     broadcasts
    -0.07
     iod
    -0.07
     prol
    -0.07
     televised
    -0.07
     assinatura
    -0.07
    POSITIVE LOGITS
     compassion
    0.13
     sympathy
    0.12
     pity
    0.11
     Compassion
    0.10
     empathy
    0.10
     solidarité
    0.10
     solidaridad
    0.10
     empat
    0.09
     empath
    0.09
     solidarity
    0.09
    Activations Density 0.025%

    No Known Activations