© 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. 7-RESID-POST-AA
    11. 752
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estors
    -0.08
     bündeln
    -0.08
     aliment
    -0.08
     другое
    -0.07
    ख
    -0.07
     usp
    -0.07
    不到
    -0.07
    дын
    -0.07
     Krypt
    -0.07
     остан
    -0.07
    POSITIVE LOGITS
    掉
    0.09
    困
    0.09
     troubled
    0.08
    ves
    0.08
     gach
    0.08
     cages
    0.08
     reinvent
    0.08
     Stuart
    0.08
     captivity
    0.08
     homes
    0.07
    Activations Density 0.030%

    No Known Activations