© 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. 47862
    Prev
    Next
    INDEX
    Explanations

    confusion and distraction

    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
     checkout
    -0.08
    <textarea
    -0.08
    944
    -0.07
     residues
    -0.07
     growing
    -0.07
    checkout
    -0.07
    annotation
    -0.07
     નોંધ
    -0.07
    <Integer
    -0.07
    IC
    -0.07
    POSITIVE LOGITS
     camouflage
    0.13
     deception
    0.13
     deceptive
    0.13
     evas
    0.13
     deceive
    0.13
     diversion
    0.12
     misleading
    0.11
     tactics
    0.11
    骗
    0.11
     ilus
    0.11
    Activations Density 0.021%

    No Known Activations