© 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. 65568
    Prev
    Next
    INDEX
    Explanations

    mirrors

    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
     historii
    -0.08
    ಾರ
    -0.08
    感
    -0.08
     compositor
    -0.07
    Javascript
    -0.07
    ಾರಿಗೆ
    -0.07
     tors
    -0.07
     Repository
    -0.07
     להצ
    -0.07
     ಪ್ರವ
    -0.07
    POSITIVE LOGITS
     Wahl
    0.08
     Giles
    0.08
    named
    0.08
     Rica
    0.08
    roach
    0.08
     Punta
    0.08
     жижиг
    0.08
     Forbes
    0.08
    cind
    0.07
    _Ph
    0.07
    Activations Density 0.001%

    No Known Activations