© 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. 6587
    Prev
    Next
    INDEX
    Explanations

    О

    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
    Después
    -0.09
    �்
    -0.09
    Efter
    -0.08
     setelah
    -0.08
    бычно
    -0.08
    ACES
    -0.08
    -after
    -0.08
    Unser
    -0.08
    can
    -0.07
     després
    -0.07
    POSITIVE LOGITS
    ργάν
    0.11
     incarn
    0.08
    ર્ગ
    0.08
    ργαν
    0.08
     arquitet
    0.08
     развити
    0.07
    _fac
    0.07
    પર
    0.07
    ф
    0.07
     ineff
    0.07
    Activations Density 0.005%

    No Known Activations