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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130738
    Prev
    Next
    INDEX
    Explanations

    Thermocouples

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __(
    -0.08
    -0.07
     Forces
    -0.07
     quad
    -0.07
    arse
    -0.07
    Collapse
    -0.07
     organs
    -0.07
     heaven
    -0.07
    ical
    -0.07
    nosis
    -0.07
    POSITIVE LOGITS
    ouple
    0.10
    Jason
    0.08
     eksport
    0.08
    هات
    0.08
    诚信
    0.08
    oui
    0.08
    bě
    0.08
     starte
    0.08
    FIRST
    0.08
    )V
    0.08
    Activations Density 0.000%

    No Known Activations