© 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. 48836
    Prev
    Next
    INDEX
    Explanations

    psychos

    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
    島
    -0.09
     typename
    -0.09
     analyzing
    -0.08
     mindset
    -0.08
    ชั่น
    -0.08
     pensée
    -0.08
     pensamiento
    -0.08
     studying
    -0.08
     рынка
    -0.08
    右翼
    -0.08
    POSITIVE LOGITS
    ocial
    0.14
    os
    0.13
    ob
    0.12
    ologic
    0.12
    culoskeletal
    0.11
    ological
    0.11
    ops
    0.11
    -be
    0.11
    ens
    0.10
    ोस
    0.10
    Activations Density 0.004%

    No Known Activations