© 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. 23-RESID-POST-AA
    11. 96597
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    Ą
    -0.08
    reichen
    -0.08
    iosa
    -0.08
    ர
    -0.08
    Gesture
    -0.07
    .create
    -0.07
     annih
    -0.07
    REG
    -0.07
    regulated
    -0.07
    gesture
    -0.07
    POSITIVE LOGITS
     ubut
    0.08
    'im
    0.08
    _z
    0.08
    _options
    0.07
    'z
    0.07
    換
    0.07
    .att
    0.07
    zit
    0.07
    'att
    0.07
     Bek
    0.07
    Activations Density 0.008%

    No Known Activations