© 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. 23-RESID-POST-AA
    6. 96649
    Prev
    Next
    INDEX
    Explanations

    univers

    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
    ileage
    -0.09
    iety
    -0.09
    iate
    -0.09
    ्शन
    -0.08
    j
    -0.08
     کیلئے
    -0.08
    inement
    -0.08
    ious
    -0.08
    imiento
    -0.08
    bootstrap
    -0.08
    POSITIVE LOGITS
     investigating
    0.08
    ән
    0.08
    онах
    0.08
    angeb
    0.08
    АР
    0.08
    .CODE
    0.08
    ожа
    0.08
    ож
    0.08
     abrupt
    0.08
     Leone
    0.08
    Activations Density 0.000%

    No Known Activations