© 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. 112383
    Prev
    Next
    INDEX
    Explanations

    in

    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
     получится
    -0.09
     Mountains
    -0.08
    ப்படி
    -0.08
     inclus
    -0.08
     prove
    -0.08
    anhas
    -0.08
    imed
    -0.08
     match
    -0.07
     goalkeeper
    -0.07
     السابقة
    -0.07
    POSITIVE LOGITS
     sekitar
    0.08
     Sweden
    0.08
    United
    0.08
     Sverige
    0.08
     Tennessee
    0.08
    Len
    0.08
    Argentina
    0.08
    Belg
    0.08
    hi
    0.08
    HOME
    0.08
    Activations Density 0.025%

    No Known Activations