Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48968
    Prev
    Next
    INDEX
    Explanations

    options

    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
     aula
    -0.08
    _sessions
    -0.08
    ameras
    -0.07
     foil
    -0.07
     پرا
    -0.07
    므로
    -0.07
     помещений
    -0.07
    _verbose
    -0.07
    حسب
    -0.07
    اتھ
    -0.07
    POSITIVE LOGITS
     XK
    0.09
     geraakt
    0.08
     wink
    0.08
    luğu
    0.08
     Dick
    0.08
     belasting
    0.08
     Dug
    0.08
    lsch
    0.08
     satan
    0.08
     stanje
    0.08
    Activations Density 0.000%

    No Known Activations