© 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. 113447
    Prev
    Next
    INDEX
    Explanations

    Solving math problems

    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
    00
    -0.08
    929
    -0.07
    140
    -0.07
     около
    -0.07
     ASAP
    -0.07
    189
    -0.07
     izvaj
    -0.07
    。そして
    -0.07
    142
    -0.07
     dicembre
    -0.07
    POSITIVE LOGITS
     précise
    0.08
     exig
    0.08
    alse
    0.08
    Contour
    0.07
     estrict
    0.07
     MES
    0.07
     meh
    0.07
     Hacker
    0.07
     boolean
    0.07
    caller
    0.07
    Activations Density 0.127%

    No Known Activations