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. 3-RESID-POST-AA
    6. 2231
    Prev
    Next
    INDEX
    Explanations

    ua

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .ov
    -0.08
     estrela
    -0.08
     Star
    -0.07
    över
    -0.07
     powerhouse
    -0.07
     Cath
    -0.07
    .openapi
    -0.07
    Notice
    -0.07
    .poster
    -0.07
    .der
    -0.07
    POSITIVE LOGITS
     readings
    0.09
     lees
    0.08
    bytes
    0.08
     Newman
    0.08
     చద
    0.08
     gaya
    0.08
     ನ
    0.08
    encija
    0.08
     पढ़
    0.07
    nj
    0.07
    Activations Density 0.000%

    No Known Activations