© 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. 113249
    Prev
    Next
    INDEX
    Explanations

    prophecy

    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
    poort
    -0.08
     கழ
    -0.08
    .rs
    -0.08
    €
    -0.07
    बाट
    -0.07
     attempt
    -0.07
    ు�
    -0.07
     కన
    -0.07
     BBB
    -0.07
    Calc
    -0.07
    POSITIVE LOGITS
     prophecy
    0.10
     Alma
    0.09
     fulfilled
    0.09
    IMA
    0.09
     cumpl
    0.09
     foret
    0.08
     ಪು
    0.08
     о
    0.08
     criticizing
    0.08
     deeds
    0.08
    Activations Density 0.006%

    No Known Activations