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

    Neuronpedia

    Jacobian LensNEW
    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. 69295
    Prev
    Next
    INDEX
    Explanations

    tip

    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
     factual
    -0.11
     faits
    -0.08
     fakta
    -0.08
     plur
    -0.07
     bale
    -0.07
    Jan
    -0.07
     wrongdoing
    -0.07
     jan
    -0.07
     procur
    -0.07
    ുവ
    -0.07
    POSITIVE LOGITS
    (depth
    0.08
     inversión
    0.08
     invertir
    0.08
     Investments
    0.08
     investir
    0.08
    0.08
     강화
    0.08
    świadc
    0.08
     inwest
    0.08
     Forsch
    0.07
    Activations Density 0.004%
    No Known Activations