© 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. 44599
    Prev
    Next
    INDEX
    Explanations

    end

    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
     settlements
    -0.09
     crunch
    -0.09
     communes
    -0.09
    sett
    -0.08
    terness
    -0.08
     kriz
    -0.08
     деклара
    -0.08
     Crunch
    -0.08
     settlement
    -0.08
    軍
    -0.08
    POSITIVE LOGITS
    oscopy
    0.14
     muc
    0.12
     Visit
    0.11
    Visit
    0.11
    .Visit
    0.10
    oscopic
    0.10
     visit
    0.10
     visites
    0.10
    _visit
    0.10
     visits
    0.10
    Activations Density 0.008%

    No Known Activations