© 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. 48620
    Prev
    Next
    INDEX
    Explanations

    کل

    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
    orted
    -0.11
     Huffington
    -0.08
    òrd
    -0.08
    ortion
    -0.08
    наг
    -0.08
    arding
    -0.08
     wrinkle
    -0.08
     Curitiba
    -0.07
    ញ
    -0.07
    aithe
    -0.07
    POSITIVE LOGITS
    assic
    0.10
    ASS
    0.10
     ASS
    0.10
    াস
    0.10
    릭
    0.10
    یدی
    0.10
    asse
    0.09
    cs
    0.09
    osed
    0.09
    ાસ
    0.09
    Activations Density 0.003%

    No Known Activations