© 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. 1105
    Prev
    Next
    INDEX
    Explanations

    Room

    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
    ോള
    -0.07
     confection
    -0.07
    是多少
    -0.07
     налич
    -0.07
     Dundee
    -0.07
     plantar
    -0.07
     neu
    -0.07
    πέ
    -0.07
    RQ
    -0.07
     Shields
    -0.07
    POSITIVE LOGITS
    yang
    0.09
     tame
    0.09
    liness
    0.08
     conven
    0.08
    室
    0.07
     люб
    0.07
    ěli
    0.07
     Garg
    0.07
     Stephens
    0.07
     valued
    0.07
    Activations Density 0.026%

    No Known Activations