© 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. 23-RESID-POST-AA
    11. 96967
    Prev
    Next
    INDEX
    Explanations

    coinc

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ıya
    -0.08
    ole
    -0.08
    -0.08
    omis
    -0.08
    aterials
    -0.07
     Lava
    -0.07
    ีพ
    -0.07
    Beh
    -0.07
    surf
    -0.07
     acom
    -0.07
    POSITIVE LOGITS
    ்ப்ப
    0.09
    pegno
    0.08
    idos
    0.08
     زخ
    0.08
    _UP
    0.08
    untu
    0.08
    p
    0.07
    ்ப்பு
    0.07
     如
    0.07
     निकाल
    0.07
    Activations Density 0.000%
    No Known Activations