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. 15-RESID-POST-AA
    6. 18919
    Prev
    Next
    INDEX
    Explanations

    and

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noticed
    -0.08
    etl
    -0.07
    -0.07
     verlet
    -0.07
    classified
    -0.07
     notified
    -0.07
    _SINGLE
    -0.07
     merr
    -0.07
     مراق
    -0.07
    Ethereum
    -0.07
    POSITIVE LOGITS
     Beziehung
    0.09
    ობ
    0.08
    үс
    0.08
     son's
    0.08
     spouse
    0.08
    ები
    0.08
     оформ
    0.08
    igeach
    0.08
     passende
    0.08
    скую
    0.08
    Activations Density 0.001%

    No Known Activations