Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 1828
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ாப்ப
    -0.08
    equipment
    -0.08
    олог
    -0.08
     Lu
    -0.08
     anc
    -0.08
    (sb
    -0.07
     sb
    -0.07
    ci
    -0.07
    по
    -0.07
     SBI
    -0.07
    POSITIVE LOGITS
    CCC
    0.08
    스트
    0.08
    ,此
    0.07
     Ham
    0.07
     Hubert
    0.07
     بما
    0.07
     تو
    0.07
     ਤਾਂ
    0.07
     방
    0.07
    ,该
    0.07
    Activations Density 0.078%

    No Known Activations