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. 2100
    Prev
    Next
    INDEX
    Explanations

    out

    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
     cybers
    -0.09
    اة
    -0.09
    hors
    -0.08
     verd
    -0.08
    aviors
    -0.08
    shopping
    -0.08
    表示
    -0.08
    älle
    -0.08
     sadd
    -0.08
     hjemmeside
    -0.08
    POSITIVE LOGITS
    गी
    0.08
     émotion
    0.08
    0.07
     आ
    0.07
     img
    0.07
    (img
    0.07
     उत्प
    0.07
    Strategy
    0.07
    大量
    0.07
    戦
    0.07
    Activations Density 0.004%

    No Known Activations