© 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. 18616
    Prev
    Next
    INDEX
    Explanations

    excerpts, descriptions

    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
     також
    -0.11
     таксама
    -0.10
     этом
    -0.10
     även
    -0.09
    ռ
    -0.09
     также
    -0.09
     myös
    -0.09
     ذلك
    -0.09
    에도
    -0.09
     tiež
    -0.09
    POSITIVE LOGITS
     excerpt
    0.15
     описание
    0.14
     describing
    0.14
     onderdeel
    0.13
     excerpts
    0.13
     description
    0.13
     incorrectly
    0.12
     parte
    0.12
     Beschreibung
    0.12
     snippet
    0.12
    Activations Density 0.066%

    No Known Activations