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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 2436
    Prev
    Next
    INDEX
    Explanations

    might

    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
     reputed
    -0.08
     cogn
    -0.08
     rad
    -0.08
     feb
    -0.07
     Oss
    -0.07
     alerta
    -0.07
     Soma
    -0.07
     MOS
    -0.07
    با
    -0.07
     punctual
    -0.07
    POSITIVE LOGITS
     nic
    0.08
     المب
    0.08
     twist
    0.07
     Primer
    0.07
     양
    0.07
    iles
    0.07
    �
    0.07
     fin
    0.07
     पत
    0.07
     بينهم
    0.07
    Activations Density 0.011%

    No Known Activations