© 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. 19-RESID-POST-AA
    11. 103029
    Prev
    Next
    INDEX
    Explanations

    implications

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    examples
    -0.08
     eigene
    -0.08
    तात
    -0.08
     describing
    -0.07
    ด้าน
    -0.07
    ैयाँ
    -0.07
     oriṣ
    -0.07
     voorbeelden
    -0.07
     descriptions
    -0.07
     samenwerken
    -0.07
    POSITIVE LOGITS
    意味着
    0.15
     implications
    0.14
     strengthens
    0.13
     reaf
    0.12
     announcement
    0.12
     renforcer
    0.12
     reinforces
    0.12
     باعث
    0.12
     invigor
    0.12
     Auswirkungen
    0.12
    Activations Density 0.057%

    No Known Activations