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. 119785
    Prev
    Next
    INDEX
    Explanations

    beat

    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
     контракт
    -0.10
    �
    -0.09
     MOQ
    -0.08
    .prefix
    -0.08
     deus
    -0.08
    穴
    -0.08
    vergleich
    -0.08
     utterly
    -0.08
     complètement
    -0.08
     sklep
    -0.07
    POSITIVE LOGITS
    Fed
    0.09
    Harvest
    0.08
     installieren
    0.08
     installé
    0.08
     installers
    0.08
     harvesting
    0.08
     Jobs
    0.07
     installed
    0.07
     job
    0.07
     Job
    0.07
    Activations Density 0.003%

    No Known Activations