© 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. 19100
    Prev
    Next
    INDEX
    Explanations

    of

    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
     =
    -0.09
    作为
    -0.08
     plantes
    -0.08
     formes
    -0.08
     basics
    -0.08
     koriste
    -0.07
    -0.07
    -0.07
    Roots
    -0.07
    =
    -0.07
    POSITIVE LOGITS
     geworden
    0.13
     многих
    0.13
     future
    0.11
     vieler
    0.11
     будущ
    0.11
     zukünft
    0.10
     дальней
    0.10
     многие
    0.10
     civilization
    0.10
     muchos
    0.10
    Activations Density 0.046%
    No Known Activations