© 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. 68590
    Prev
    Next
    INDEX
    Explanations

    UTF-8 encoding

    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
     Ratio
    -0.07
    -0.07
     Kirch
    -0.07
     KE
    -0.07
     эр
    -0.07
     Ney
    -0.07
     комплекс
    -0.07
    Ratio
    -0.07
     considering
    -0.07
     Busch
    -0.07
    POSITIVE LOGITS
    _constructor
    0.10
     starter
    0.10
     começa
    0.09
     télécharger
    0.09
     starters
    0.09
     تبدأ
    0.08
     commencer
    0.08
     comien
    0.08
    ূল
    0.08
     NSData
    0.08
    Activations Density 0.001%
    No Known Activations