© 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. 69841
    Prev
    Next
    INDEX
    Explanations

    marx/marxism

    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
     திற
    -0.08
     퍼
    -0.08
     Secrets
    -0.08
     Shots
    -0.08
     publiko
    -0.08
    tai
    -0.08
     neut
    -0.08
    adakan
    -0.08
    mailto
    -0.08
     corona
    -0.07
    POSITIVE LOGITS
    观点
    0.10
     doctrine
    0.09
     oppressed
    0.09
     capitalist
    0.09
     Marx
    0.09
     clas
    0.09
     framework
    0.09
     класс
    0.08
     ideology
    0.08
     doctrines
    0.08
    Activations Density 0.003%

    No Known Activations