© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 108249
    Prev
    Next
    INDEX
    Explanations

    family relationships

    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
     lush
    -0.09
     bustling
    -0.08
     стой
    -0.08
     ચલ
    -0.08
    enable
    -0.08
    	enable
    -0.08
     impul
    -0.08
     profanity
    -0.08
     sinc
    -0.08
    (argc
    -0.08
    POSITIVE LOGITS
     relatives
    0.15
     nieces
    0.14
     родствен
    0.14
     acquaintances
    0.13
     cousin
    0.13
     cousins
    0.13
     relacionamento
    0.12
    联系人
    0.12
     niece
    0.12
     रिश्त
    0.12
    Activations Density 0.043%

    No Known Activations