© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102442
    Prev
    Next
    INDEX
    Explanations

    okay

    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
     jeweiligen
    -0.09
    ekl
    -0.08
    /oder
    -0.08
    respect
    -0.08
    ervation
    -0.08
     entirety
    -0.08
    ’Es
    -0.08
    estones
    -0.08
    arante
    -0.08
    そして
    -0.08
    POSITIVE LOGITS
     if
    0.16
     with
    0.14
    ,
    0.12
     якщо
    0.12
     dacă
    0.12
     अगर
    0.12
    .
    0.12
     যদি
    0.11
     as
    0.11
     если
    0.11
    Activations Density 0.009%

    No Known Activations