© 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. 43539
    Prev
    Next
    INDEX
    Explanations

    sonnets and "volta"

    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
    ISOString
    -0.09
    leist
    -0.08
    see
    -0.08
    avase
    -0.08
    ธุ
    -0.08
     стер
    -0.08
    ū
    -0.07
     شأن
    -0.07
     fascinating
    -0.07
    بد
    -0.07
    POSITIVE LOGITS
     Dreh
    0.08
     Lehrer
    0.08
     शिक्षक
    0.07
     pedag
    0.07
     lyrics
    0.07
     professores
    0.07
     directeur
    0.07
     reviews
    0.07
    歌词
    0.07
     profesor
    0.07
    Activations Density 0.000%

    No Known Activations