© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18419
    Prev
    Next
    INDEX
    Explanations

    to

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’s
    -0.10
    entes
    -0.09
    \"
    -0.09
     icons
    -0.09
    's
    -0.08
    یا
    -0.08
    _icons
    -0.08
    ’ém
    -0.08
     Icons
    -0.08
     ['./
    -0.08
    POSITIVE LOGITS
     two
    0.17
     three
    0.17
     high
    0.15
     four
    0.15
     nearest
    0.15
     তিন
    0.15
     five
    0.15
     तीन
    0.14
     ثلاثة
    0.14
     ಮೂರು
    0.14
    Activations Density 0.004%

    No Known Activations