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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102780
    Prev
    Next
    INDEX
    Explanations

    Until

    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
     સલ
    -0.09
     সম্প
    -0.08
     evitar
    -0.08
     প্রত
    -0.08
     સાર
    -0.08
     অভিয
    -0.08
     বাদ
    -0.08
    vres
    -0.08
     ভালো
    -0.08
     কর্ম
    -0.08
    POSITIVE LOGITS
    -now
    0.10
    _now
    0.10
    Logged
    0.09
    /log
    0.09
    /use
    0.09
    -test
    0.09
    itter
    0.08
    /application
    0.08
    -tested
    0.08
    िट
    0.08
    Activations Density 0.020%

    No Known Activations