© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48586
    Prev
    Next
    INDEX
    Explanations

    Knowledge retention

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gửi
    -0.08
     развед
    -0.07
     Editor
    -0.07
    unguza
    -0.07
    裁
    -0.07
     projecten
    -0.07
     dater
    -0.07
    наст
    -0.07
     disagreements
    -0.07
     pö
    -0.07
    POSITIVE LOGITS
     retention
    0.26
    Retention
    0.23
     consolidation
    0.19
     retaining
    0.19
     retain
    0.18
     закреп
    0.18
     assimilation
    0.18
     consolidate
    0.17
     reinforce
    0.17
     cement
    0.17
    Activations Density 0.073%

    No Known Activations