© 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. 48921
    Prev
    Next
    INDEX
    Explanations

    pudd

    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
    аторов
    -0.10
     Cortex
    -0.09
    ATOR
    -0.09
    ATORS
    -0.09
    atoren
    -0.08
    ਾਈ
    -0.08
     Φ
    -0.08
    atórios
    -0.08
    AT
    -0.08
    атора
    -0.08
    POSITIVE LOGITS
    le
    0.15
     pudd
    0.14
     पोख
    0.11
    plings
    0.11
    les
    0.10
    marks
    0.10
     pond
    0.10
    (le
    0.10
    leton
    0.09
     weers
    0.09
    Activations Density 0.003%

    No Known Activations