© 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. 29772
    Prev
    Next
    INDEX
    Explanations

    anonymity/confidentiality

    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
     parse
    -0.08
     bounding
    -0.08
     multiplying
    -0.08
     dividing
    -0.08
     multiply
    -0.08
     multiplied
    -0.08
     evident
    -0.08
     busy
    -0.08
    Multip
    -0.07
     maritime
    -0.07
    POSITIVE LOGITS
     anonim
    0.21
     anonymity
    0.21
    匿名
    0.21
     anonymous
    0.17
    anonymous
    0.17
     Anonymous
    0.17
     anonymously
    0.17
    Anonymous
    0.17
     confidentiality
    0.16
     anonym
    0.16
    Activations Density 0.035%

    No Known Activations