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. 77038
    Prev
    Next
    INDEX
    Explanations

    MGMT/Talking Heads

    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
     voet
    -0.08
     violently
    -0.08
     Hebrews
    -0.08
     ফুট
    -0.08
     hosp
    -0.07
     voyages
    -0.07
    -serv
    -0.07
     plantations
    -0.07
    branch
    -0.07
     offrir
    -0.07
    POSITIVE LOGITS
    .JSON
    0.09
     boutique
    0.08
     xan
    0.08
     Boutique
    0.08
     pastel
    0.08
     sx
    0.08
     mün
    0.08
     coined
    0.08
    روج
    0.08
    颖
    0.08
    Activations Density 0.040%

    No Known Activations