© 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. 2672
    Prev
    Next
    INDEX
    Explanations

    forever

    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
     Abr
    -0.08
    sit
    -0.07
     Mig
    -0.07
     Mountain
    -0.07
    gw
    -0.07
    FID
    -0.07
    .nav
    -0.07
    _REG
    -0.07
    RAL
    -0.07
     טע
    -0.07
    POSITIVE LOGITS
     Tin
    0.08
     tin
    0.07
     damn
    0.07
     Boy
    0.07
    �
    0.07
    0.07
     ton
    0.07
     dumb
    0.07
     caus
    0.07
    讯
    0.07
    Activations Density 0.002%
    No Known Activations