© 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. 49773
    Prev
    Next
    INDEX
    Explanations

    .

    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
    دع
    -0.08
    ிள
    -0.08
    illation
    -0.08
    .vertical
    -0.08
    weiten
    -0.08
     Swarovski
    -0.07
     Feier
    -0.07
     imam
    -0.07
    _use
    -0.07
     шақ
    -0.07
    POSITIVE LOGITS
    653
    0.09
    ándose
    0.09
    145
    0.07
    654
    0.07
     resten
    0.07
     Anc
    0.07
     hostility
    0.07
     Lexer
    0.07
     medd
    0.07
    416
    0.07
    Activations Density 0.001%

    No Known Activations