© 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. 47262
    Prev
    Next
    INDEX
    Explanations

    desensitization

    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
     DIR
    -0.08
     السنة
    -0.08
     ciencia
    -0.07
     kingdom
    -0.07
    	Optional
    -0.07
     بری
    -0.07
    正版
    -0.07
    科学
    -0.07
     Bharat
    -0.07
     biens
    -0.07
    POSITIVE LOGITS
     inoc
    0.10
     increasingly
    0.09
     progressively
    0.09
     endurance
    0.09
     gradually
    0.08
     Frequently
    0.08
     walkthrough
    0.08
     irritation
    0.08
     hypnosis
    0.08
     progressivement
    0.08
    Activations Density 0.006%

    No Known Activations