© 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. 7-RESID-POST-AA
    11. 1106
    Prev
    Next
    INDEX
    Explanations

    unit conversions km/h m/s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    担
    -0.09
     toplum
    -0.08
    售
    -0.08
    사회
    -0.08
    Inheritance
    -0.08
    实力
    -0.08
    �
    -0.08
     matur
    -0.08
    ымды
    -0.08
     مخاط
    -0.08
    POSITIVE LOGITS
     �
    0.09
     worldwide
    0.08
     fein
    0.08
     underground
    0.08
     Earth's
    0.08
     weltweit
    0.08
     terrestrial
    0.08
     extrater
    0.08
    converted
    0.08
    abbr
    0.08
    Activations Density 0.050%

    No Known Activations