© 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. 11-RESID-POST-AA
    11. 54625
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paga
    -0.08
     cus
    -0.08
     payoff
    -0.08
     stakeholder
    -0.08
    .The
    -0.07
     costes
    -0.07
     decode
    -0.07
     zahlen
    -0.07
    nage
    -0.07
     karde
    -0.07
    POSITIVE LOGITS
    Jn
    0.08
    ,val
    0.08
    과
    0.08
    �
    0.08
     Abr
    0.07
    Alg
    0.07
    closed
    0.07
    alg
    0.07
    Abr
    0.07
    歡
    0.07
    Activations Density 0.014%

    No Known Activations