© 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. 108412
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
    ią
    -0.09
    -transfer
    -0.08
    _ent
    -0.08
    iap
    -0.08
    -week
    -0.08
    rid
    -0.07
    hyp
    -0.07
     gặp
    -0.07
    rb
    -0.07
    'ag
    -0.07
    POSITIVE LOGITS
     Actually
    0.12
    Actually
    0.11
     actually
    0.09
     zviri
    0.09
     kunjalo
    0.08
    بت
    0.08
     wait
    0.08
     konserv
    0.08
     zvino
    0.08
     puhul
    0.08
    Activations Density 0.181%

    No Known Activations