© 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. 1089
    Prev
    Next
    INDEX
    Explanations

    Sailing and ships

    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
     deposited
    -0.08
    reference
    -0.08
     revoke
    -0.08
    prox
    -0.08
    awr
    -0.07
     moistur
    -0.07
    .reference
    -0.07
     próximo
    -0.07
    vir
    -0.07
    pressure
    -0.07
    POSITIVE LOGITS
     সক্ষম
    0.10
     wagen
    0.10
     fleets
    0.09
     πραγματοποι
    0.09
     boats
    0.09
     hubs
    0.09
     Barca
    0.09
     திற
    0.09
     দক্ষ
    0.09
     skilled
    0.09
    Activations Density 0.011%

    No Known Activations