© 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. 103116
    Prev
    Next
    INDEX
    Explanations

    Large numbers and calculations

    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
     jeweiligen
    -0.09
     "
    -0.08
     các
    -0.08
     tegev
    -0.08
    nungszeiten
    -0.08
    uoj
    -0.08
    ഴ
    -0.08
     certains
    -0.08
     respective
    -0.07
     travaux
    -0.07
    POSITIVE LOGITS
     without
    0.09
     ακόμα
    0.08
    ��
    0.08
     seventh
    0.08
     mbola
    0.08
    without
    0.07
    Other
    0.07
     अगर
    0.07
    ORAGE
    0.07
    shint
    0.07
    Activations Density 0.175%

    No Known Activations