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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13365
    Prev
    Next
    INDEX
    Explanations

    .\{

    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
    融
    -0.08
     scrap
    -0.07
    override
    -0.07
    แกรม
    -0.07
     sponsorship
    -0.07
    (sc
    -0.07
    添
    -0.07
    ค้
    -0.07
    _OVERRIDE
    -0.07
    ো
    -0.07
    POSITIVE LOGITS
     consequent
    0.08
     repe
    0.08
     wykon
    0.08
     repeating
    0.08
     Hor
    0.08
     подраз
    0.08
     alternating
    0.07
     altern
    0.07
     Ple
    0.07
    Ple
    0.07
    Activations Density 0.000%

    No Known Activations