© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1452
    Prev
    Next
    INDEX
    Explanations

    triple backticks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Munich
    -0.08
     ó
    -0.08
    ym
    -0.08
     Couple
    -0.08
    码
    -0.08
     먹
    -0.08
     chemo
    -0.07
     masu
    -0.07
     Mos
    -0.07
     grab
    -0.07
    POSITIVE LOGITS
     bothers
    0.08
    سی
    0.08
     bel
    0.08
     SWOT
    0.07
    Salle
    0.07
    是什么意思
    0.07
    .Compiler
    0.07
    _subscription
    0.07
     gay
    0.07
    _ENUM
    0.07
    Activations Density 0.012%

    No Known Activations