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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 102555
    Prev
    Next
    INDEX
    Explanations

    far

    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
    ábado
    -0.08
     Now
    -0.08
     oldukça
    -0.08
    now
    -0.08
     muitos
    -0.08
     još
    -0.08
     Around
    -0.08
    Now
    -0.07
     સાથે
    -0.07
     talvez
    -0.07
    POSITIVE LOGITS
     worse
    0.11
     préférable
    0.10
     cheaper
    0.10
     बढी
    0.10
     sneller
    0.10
     kuliko
    0.10
     preferable
    0.10
     বেশি
    0.10
     superior
    0.10
     быстрее
    0.10
    Activations Density 0.024%

    No Known Activations