© 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. 19-RESID-POST-AA
    11. 18830
    Prev
    Next
    INDEX
    Explanations

    academic language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vibe
    -0.18
     vibes
    -0.18
     kinda
    -0.17
     pesky
    -0.16
     �
    -0.16
     veggies
    -0.15
     fucking
    -0.15
     lol
    -0.15
     shitty
    -0.15
     weird
    -0.15
    POSITIVE LOGITS
     methodological
    0.15
     interdisciplinary
    0.15
    我国
    0.15
     interdiscip
    0.14
     principally
    0.14
     pedagog
    0.14
    开展
    0.13
     multidisciplinary
    0.13
     Proceedings
    0.13
     analyses
    0.13
    Activations Density 0.374%

    No Known Activations