© 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. 23-RESID-POST-AA
    11. 51240
    Prev
    Next
    INDEX
    Explanations

    Separators

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sources
    -0.12
    _sources
    -0.11
    SRC
    -0.10
     sources
    -0.10
    Source
    -0.10
    .),
    -0.09
    Src
    -0.09
    .Source
    -0.09
    _source
    -0.09
     Sources
    -0.09
    POSITIVE LOGITS
    ─
    0.11
     ...↵↵↵
    0.11
     …↵
    0.10
     Change
    0.10
     ...↵
    0.10
     Third
    0.10
     Locale
    0.10
     ...↵↵
    0.10
     �
    0.10
     Logo
    0.09
    Activations Density 0.002%

    No Known Activations