© 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. 102728
    Prev
    Next
    INDEX
    Explanations

    hold

    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
     portanto
    -0.08
     UINavigation
    -0.07
     således
    -0.07
     bomen
    -0.07
     SITE
    -0.07
     hourly
    -0.07
     alati
    -0.07
    ౖ
    -0.07
     provavelmente
    -0.07
    ಂದು
    -0.07
    POSITIVE LOGITS
    Holding
    0.12
    Hold
    0.12
     holding
    0.11
    _hold
    0.11
    -held
    0.10
     briefly
    0.10
     રાખ
    0.10
     halten
    0.10
     Holding
    0.10
    _pause
    0.10
    Activations Density 0.002%

    No Known Activations