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. 65562
    Prev
    Next
    INDEX
    Explanations

    dec

    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
    mgr
    -0.08
     gui
    -0.08
    gui
    -0.08
     Swedish
    -0.08
    persoon
    -0.08
    iscal
    -0.07
     Offices
    -0.07
     svensk
    -0.07
     plaatse
    -0.07
    _Insert
    -0.07
    POSITIVE LOGITS
    数组
    0.10
    _ARRAY
    0.10
     array
    0.09
    (array
    0.09
     arrays
    0.09
    .array
    0.09
     배열
    0.09
     массива
    0.08
     ndarray
    0.08
    -array
    0.08
    Activations Density 0.002%

    No Known Activations