© 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. 5645
    Prev
    Next
    INDEX
    Explanations

    new

    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
     фит
    -0.09
     conosco
    -0.09
     �
    -0.08
     moun
    -0.08
     ホ
    -0.08
    птом
    -0.08
     folgen
    -0.08
     href
    -0.08
    Вс
    -0.08
    зіцца
    -0.08
    POSITIVE LOGITS
    -energy
    0.08
     Current
    0.08
    .current
    0.08
    current
    0.08
     Third
    0.08
     Left
    0.08
    能源
    0.08
    _CURRENT
    0.08
    -style
    0.08
     currents
    0.08
    Activations Density 0.002%

    No Known Activations