© 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. 11-RESID-POST-AA
    11. 70111
    Prev
    Next
    INDEX
    Explanations

    Conversational dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arvio
    -0.08
    MIL
    -0.08
     waarop
    -0.08
     pare
    -0.07
    _eval
    -0.07
     erhältlich
    -0.07
     attenzione
    -0.07
     evaluating
    -0.07
     assess
    -0.07
     osią
    -0.07
    POSITIVE LOGITS
     reluctantly
    0.12
     Tent
    0.09
     finalement
    0.09
     пусть
    0.09
    于是
    0.09
     festen
    0.09
     gladly
    0.09
    暂
    0.09
     beschlossen
    0.09
     wholeheartedly
    0.09
    Activations Density 0.098%

    No Known Activations