© 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. 19084
    Prev
    Next
    INDEX
    Explanations

    Numbers and percentages

    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
     simpler
    -0.09
    :Set
    -0.09
     bigger
    -0.08
     называется
    -0.08
     knows
    -0.08
    _SET
    -0.08
     such
    -0.08
    是
    -0.08
     like
    -0.08
     belonged
    -0.08
    POSITIVE LOGITS
    ≈
    0.18
     �
    0.17
    approximately
    0.15
     約
    0.13
    approx
    0.13
     약
    0.13
     approximately
    0.13
     aproximadamente
    0.13
     ಸುಮಾರು
    0.13
    約
    0.12
    Activations Density 0.020%

    No Known Activations