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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 71088
    Prev
    Next
    INDEX
    Explanations

    challenging, difficult

    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
     fotos
    -0.08
     baskets
    -0.08
     पत
    -0.08
     ફોટ
    -0.07
     puestos
    -0.07
     paths
    -0.07
    照片
    -0.07
     horizons
    -0.07
    ستن
    -0.07
     niches
    -0.07
    POSITIVE LOGITS
     antics
    0.13
     stubborn
    0.13
     rebellious
    0.13
     troublesome
    0.12
     notorious
    0.12
    ubborn
    0.12
     temperament
    0.12
     misch
    0.11
     notoriously
    0.11
    拒
    0.10
    Activations Density 0.115%

    No Known Activations