© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96887
    Prev
    Next
    INDEX
    Explanations

    Non-English language texts

    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
    strijd
    -0.09
     Inspect
    -0.08
    ഗ്
    -0.08
    mented
    -0.08
    Գ
    -0.08
     Regl
    -0.07
     спад
    -0.07
     верх
    -0.07
     Barcl
    -0.07
    erders
    -0.07
    POSITIVE LOGITS
    ação
    0.11
    andum
    0.11
    ación
    0.11
    abo
    0.10
    itação
    0.10
    ações
    0.10
    説明
    0.09
    itar
    0.09
    ando
    0.09
    aciones
    0.09
    Activations Density 0.002%

    No Known Activations