© 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. 31360
    Prev
    Next
    INDEX
    Explanations

    net

    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
     relo
    -0.09
     relocating
    -0.09
    -legged
    -0.08
     relocation
    -0.08
     relocate
    -0.08
     relóg
    -0.08
     reload
    -0.08
    .codehaus
    -0.07
    Grpc
    -0.07
     relocated
    -0.07
    POSITIVE LOGITS
    上的
    0.10
     scams
    0.09
     surfing
    0.09
     opini
    0.09
     etiquette
    0.09
     opinion
    0.08
    /social
    0.08
     conspiracy
    0.08
     dw
    0.08
     usernames
    0.08
    Activations Density 0.038%

    No Known Activations