© 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. 63769
    Prev
    Next
    INDEX
    Explanations

    permanently marked/remembered

    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
     timezone
    -0.09
     മുമ്പ
    -0.08
    timezone
    -0.07
    anca
    -0.07
     wäre
    -0.07
    -range
    -0.07
    ober
    -0.07
    ishop
    -0.07
     istiq
    -0.07
     imkan
    -0.07
    POSITIVE LOGITS
     etched
    0.15
    刻
    0.10
    铭
    0.10
     woven
    0.10
     основу
    0.09
    Inte
    0.09
    ใจ
    0.09
    ไว้
    0.08
     embossed
    0.08
     الرمال
    0.08
    Activations Density 0.024%

    No Known Activations