© 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. 64052
    Prev
    Next
    INDEX
    Explanations

    Statements of fact/predictions

    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
     yata
    -0.08
     semelhantes
    -0.08
    klary
    -0.07
    kräft
    -0.07
    ombe
    -0.07
    _Enable
    -0.07
     unde
    -0.07
    frastruktur
    -0.07
     similar
    -0.07
     Addison
    -0.07
    POSITIVE LOGITS
    情况下
    0.08
     assumption
    0.08
     ক্ষেত্রে
    0.07
     attainable
    0.07
     нашем
    0.07
     המשת
    0.07
     feasible
    0.07
    ‌هایی
    0.07
    Technique
    0.07
     circumstance
    0.07
    Activations Density 0.068%

    No Known Activations