© 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. 18846
    Prev
    Next
    INDEX
    Explanations

    So

    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
     også
    -0.14
     auch
    -0.13
     Também
    -0.12
     sommige
    -0.12
     também
    -0.12
     també
    -0.12
     tamén
    -0.12
     bazı
    -0.12
     också
    -0.12
     également
    -0.12
    POSITIVE LOGITS
     then
    0.14
     I'll
    0.14
     тогда
    0.13
     Then
    0.12
    Then
    0.12
    I'll
    0.11
    Entonces
    0.11
     Тогда
    0.11
     thus
    0.10
     better
    0.10
    Activations Density 0.054%

    No Known Activations