© 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. 96271
    Prev
    Next
    INDEX
    Explanations

    Math computations

    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
    tonu
    -0.09
     homofil
    -0.09
     berdi
    -0.09
     enca
    -0.09
     enw
    -0.08
     ამბ
    -0.08
     ahau
    -0.08
    awanda
    -0.08
     kaua
    -0.08
     lesbisk
    -0.08
    POSITIVE LOGITS
    12
    0.09
    13
    0.09
    75
    0.09
    963
    0.08
    _Q
    0.08
    _CODE
    0.08
    111
    0.08
    .Q
    0.08
     Qt
    0.08
    8
    0.08
    Activations Density 0.108%

    No Known Activations