© 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. 48557
    Prev
    Next
    INDEX
    Explanations

    settings options

    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
    	stmt
    -0.08
     Directive
    -0.08
    unnable
    -0.08
     BOS
    -0.08
    Directive
    -0.08
    	cmd
    -0.08
    oncé
    -0.07
     Columbus
    -0.07
    	msg
    -0.07
     stos
    -0.07
    POSITIVE LOGITS
    Privacy
    0.15
     preferencias
    0.15
    Advanced
    0.14
     privacy
    0.14
    .General
    0.14
    .Appearance
    0.14
    Preferences
    0.14
     preferences
    0.14
     appearance
    0.14
     General
    0.14
    Activations Density 0.024%

    No Known Activations