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. 44750
    Prev
    Next
    INDEX
    Explanations

    tail

    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
     universe
    -0.08
    Universe
    -0.07
    un
    -0.07
     uni
    -0.07
    ECT
    -0.07
    課
    -0.07
    hip
    -0.07
     стоят
    -0.07
    庫
    -0.07
    hi
    -0.07
    POSITIVE LOGITS
     cheek
    0.10
     Schwanz
    0.09
    尾
    0.09
     wag
    0.08
     acar
    0.08
    wag
    0.08
    pertise
    0.08
     antics
    0.08
    杆
    0.08
    -sn
    0.08
    Activations Density 0.011%

    No Known Activations