© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 31623
    Prev
    Next
    INDEX
    Explanations

    Pompeii

    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
     responsible
    -0.08
     процесс
    -0.07
     Scoop
    -0.07
     ọ
    -0.07
     Cody
    -0.07
    оч
    -0.07
     procesos
    -0.07
     مرح
    -0.07
     Dif
    -0.07
     vend
    -0.07
    POSITIVE LOGITS
    wrong
    0.08
    classic
    0.08
    般
    0.08
     �
    0.08
     classique
    0.08
    usių
    0.08
     sinking
    0.08
     знаменит
    0.08
     villes
    0.08
     shut
    0.08
    Activations Density 0.002%

    No Known Activations