© 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. 45374
    Prev
    Next
    INDEX
    Explanations

    or

    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
     che
    -0.08
     rispetto
    -0.08
     nhân
    -0.08
     seva
    -0.07
    竞技
    -0.07
     hacks
    -0.07
     verlet
    -0.07
     espos
    -0.07
     começa
    -0.07
     verso
    -0.07
    POSITIVE LOGITS
     depending
    0.11
     dependiendo
    0.10
    ”
    0.10
    depending
    0.09
     unpredict
    0.09
     dependendo
    0.09
     Depending
    0.08
     бывает
    0.08
    [];↵↵
    0.08
     AIM
    0.07
    Activations Density 0.031%

    No Known Activations