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. 59
    Prev
    Next
    INDEX
    Explanations

    possibility or uncertainty

    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
    Lev
    -0.08
    !!!!↵
    -0.08
     believable
    -0.08
    降
    -0.08
    Carga
    -0.08
     chicks
    -0.08
     その他
    -0.07
    名前
    -0.07
    LAB
    -0.07
    !!!!↵↵
    -0.07
    POSITIVE LOGITS
    :",
    0.08
    :")↵
    0.08
     you
    0.08
     جد
    0.08
     असून
    0.08
    :",↵
    0.08
    :"
    0.07
     XXX
    0.07
     XYZ
    0.07
    note
    0.07
    Activations Density 0.126%

    No Known Activations