© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102431
    Prev
    Next
    INDEX
    Explanations

    same

    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
     both
    -0.11
     as
    -0.10
     unless
    -0.09
     everything
    -0.08
     all
    -0.08
    (always
    -0.08
     bisherigen
    -0.08
     (*
    -0.08
     etc
    -0.08
     such
    -0.08
    POSITIVE LOGITS
     voidaan
    0.11
    could
    0.11
     podría
    0.10
     could
    0.10
     waxaa
    0.10
     võiks
    0.09
     podria
    0.09
     wuxuu
    0.09
     Waxaa
    0.09
     Bisa
    0.09
    Activations Density 0.011%

    No Known Activations