© 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. 50235
    Prev
    Next
    INDEX
    Explanations

    ot

    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
     ś
    -0.08
     Pier
    -0.07
     override
    -0.07
     Override
    -0.07
    -G
    -0.07
    תה
    -0.07
     mõ
    -0.07
    ути
    -0.07
     अन्त
    -0.07
    תו
    -0.07
    POSITIVE LOGITS
    ipos
    0.12
    ip
    0.11
    ipop
    0.09
     ass
    0.09
    ipes
    0.08
     ip
    0.08
    idle
    0.08
    assin
    0.08
    drag
    0.08
     Fais
    0.08
    Activations Density 0.000%

    No Known Activations