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. 56242
    Prev
    Next
    INDEX
    Explanations

    onomastics

    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
    无需
    -0.08
     ken
    -0.08
    Ak
    -0.08
     sürd
    -0.08
     enga
    -0.07
    ाक
    -0.07
    Mm
    -0.07
    ුව
    -0.07
    为了
    -0.07
    Donald
    -0.07
    POSITIVE LOGITS
     Theology
    0.09
    ænd
    0.09
     Origins
    0.08
     theology
    0.08
     Stones
    0.08
     Philosophy
    0.08
     कुल
    0.08
     Tree
    0.08
     Patterns
    0.08
     صن
    0.08
    Activations Density 0.004%

    No Known Activations