© 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. 19629
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    קרה
    -0.10
    կա
    -0.09
    -achọ
    -0.09
    ərək
    -0.09
    hlelo
    -0.09
    'ihu
    -0.09
    -acde
    -0.08
    իզ
    -0.08
    tje
    -0.08
    -də
    -0.08
    POSITIVE LOGITS
     asupra
    0.15
     on
    0.13
     على
    0.12
    گذار
    0.11
    ful
    0.11
    iveness
    0.11
     علينا
    0.10
    ivity
    0.10
    uation
    0.10
     پذ
    0.10
    Activations Density 0.029%

    No Known Activations