© 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. 102565
    Prev
    Next
    INDEX
    Explanations

    use

    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
    ,...↵↵
    -0.10
     etc
    -0.10
    。...↵↵
    -0.09
    ....↵
    -0.09
     Everything
    -0.09
     …↵
    -0.09
    everything
    -0.09
    Everything
    -0.09
     everything
    -0.09
    ...↵
    -0.09
    POSITIVE LOGITS
     terminology
    0.20
     Begriff
    0.19
     terms
    0.18
     termes
    0.18
     términos
    0.17
     термин
    0.17
     notation
    0.17
     istil
    0.16
     term
    0.16
    terms
    0.15
    Activations Density 0.016%

    No Known Activations