© 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. 78112
    Prev
    Next
    INDEX
    Explanations

    Polish

    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
     anderem
    -0.08
     programmed
    -0.08
    ்சி
    -0.07
     hurricane
    -0.07
     chal
    -0.07
     tím
    -0.07
     Troubles
    -0.07
     warfare
    -0.07
    Tec
    -0.07
    Fingerprint
    -0.07
    POSITIVE LOGITS
     Compr
    0.09
     compr
    0.08
     நாட்ட
    0.08
    VS
    0.07
     Heidelberg
    0.07
     Innoc
    0.07
     Gros
    0.07
    ország
    0.07
     XIII
    0.07
     красав
    0.07
    Activations Density 0.003%

    No Known Activations