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

    Neuronpedia

    Jacobian LensNEW
    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. 49317
    Prev
    Next
    INDEX
    Explanations

    Pl

    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
     получает
    -0.09
     касается
    -0.09
     maggio
    -0.08
     прям
    -0.08
     afbeeld
    -0.08
    arschijnlijk
    -0.08
    مم
    -0.08
     выбира
    -0.08
     может
    -0.08
     зах
    -0.08
    POSITIVE LOGITS
    aton
    0.13
    των
    0.09
    ato
    0.08
    usto
    0.08
    ató
    0.07
    Rl
    0.07
    alu
    0.07
    inius
    0.07
    ativity
    0.07
    ra
    0.07
    Activations Density 0.000%

    No Known Activations