Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49280
    Prev
    Next
    INDEX
    Explanations

    cross product determinant computations

    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
     chế
    -0.08
     workouts
    -0.08
     survivors
    -0.08
     bursts
    -0.08
     vigorous
    -0.07
     evenings
    -0.07
     bouts
    -0.07
     tapes
    -0.07
     campaigns
    -0.07
     sermons
    -0.07
    POSITIVE LOGITS
     IERC
    0.10
    ตำรวจ
    0.09
     
    0.08
    ’яз
    0.08
     polícia
    0.08
     faker
    0.08
     río
    0.08
    水县
    0.07
    icion
    0.07
     Poison
    0.07
    Activations Density 0.003%

    No Known Activations