© 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. 11-RESID-POST-AA
    11. 24593
    Prev
    Next
    INDEX
    Explanations

    2

    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
     حرارة
    -0.08
     heures
    -0.08
     godzin
    -0.08
     Ang
    -0.08
     Hamilton
    -0.08
     RFID
    -0.07
     degradation
    -0.07
    כר
    -0.07
    Ang
    -0.07
    ależ
    -0.07
    POSITIVE LOGITS
    -shop
    0.08
     তৈরি
    0.07
     grundleg
    0.07
     Та
    0.07
    ensional
    0.07
    _uuid
    0.07
    urika
    0.07
    (send
    0.07
    理念
    0.07
    mey
    0.07
    Activations Density 0.031%

    No Known Activations