© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1263
    Prev
    Next
    INDEX
    Explanations

    answer

    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
    xff
    -0.08
     adequately
    -0.08
    бия
    -0.08
    еб
    -0.07
     waɗ
    -0.07
    opedic
    -0.07
    xffffff
    -0.07
    Git
    -0.07
     outspoken
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    itsin
    0.08
     Mathemat
    0.07
     formulas
    0.07
    uciones
    0.07
     decimals
    0.07
     provis
    0.07
     Requested
    0.07
    Mayor
    0.07
     solicitudes
    0.07
     gore
    0.07
    Activations Density 0.073%

    No Known Activations