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. 65194
    Prev
    Next
    INDEX
    Explanations

    user

    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
    ensi
    -0.08
     Enumerator
    -0.08
    ooka
    -0.08
     soi
    -0.08
    써
    -0.08
     contam
    -0.07
     βιβ
    -0.07
    باب
    -0.07
     ماحول
    -0.07
     solitude
    -0.07
    POSITIVE LOGITS
     wants
    0.11
     want
    0.10
    指出
    0.09
     хочет
    0.09
     asked
    0.09
     মনে
    0.09
     interested
    0.09
    觉得
    0.09
    ภาพ
    0.09
     wanting
    0.08
    Activations Density 0.048%

    No Known Activations