© 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. 11-RESID-POST-AA
    11. 94974
    Prev
    Next
    INDEX
    Explanations

    PCI data security

    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
     वैज्ञानिक
    -0.09
     presidencial
    -0.08
     राजनीति
    -0.08
     pictures
    -0.08
     inaccuracies
    -0.08
     groenten
    -0.08
    ieties
    -0.08
    orphism
    -0.08
     Heimat
    -0.08
     irrational
    -0.08
    POSITIVE LOGITS
     PCI
    0.09
     certification
    0.09
     conformité
    0.09
    PCI
    0.09
     tighter
    0.08
    connect
    0.08
    业务
    0.08
     compliance
    0.08
    -certified
    0.07
    认证
    0.07
    Activations Density 0.005%

    No Known Activations