© 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. 18989
    Prev
    Next
    INDEX
    Explanations

    aware

    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
     наши
    -0.11
     разные
    -0.11
     cosas
    -0.10
     нашу
    -0.10
     unsere
    -0.10
     nasze
    -0.10
     Our
    -0.10
     nossas
    -0.10
     наша
    -0.10
     nuestra
    -0.10
    POSITIVE LOGITS
     okenn
    0.15
     कुनै
    0.14
     unrhyw
    0.14
     ಯಾವುದೇ
    0.14
     adanya
    0.14
     حدوث
    0.14
     anumang
    0.14
     any
    0.14
     որևէ
    0.14
     ऐसे
    0.13
    Activations Density 0.016%

    No Known Activations