© 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. 23-RESID-POST-AA
    11. 97718
    Prev
    Next
    INDEX
    Explanations

    settlers and settlements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Islamist
    -0.11
     Libya
    -0.10
     esports
    -0.09
     planetary
    -0.09
     ASEAN
    -0.09
     Qatar
    -0.09
     wereldwijd
    -0.09
     Neymar
    -0.09
    宮
    -0.09
     Doha
    -0.09
    POSITIVE LOGITS
     settlers
    0.24
     settlement
    0.18
     patroon
    0.18
     sett
    0.17
     Settlement
    0.15
    Settlement
    0.15
     pioneer
    0.15
     pione
    0.15
     settlements
    0.15
     Sett
    0.15
    Activations Density 0.049%

    No Known Activations