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. 1938
    Prev
    Next
    INDEX
    Explanations

    запр

    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
    prod
    -0.08
     cylind
    -0.08
     cleavage
    -0.08
     plur
    -0.07
    uctus
    -0.07
     Ish
    -0.07
     cure
    -0.07
    471
    -0.07
     ICD
    -0.07
     sống
    -0.07
    POSITIVE LOGITS
    Vent
    0.08
     Ho
    0.08
    करण
    0.08
    Bis
    0.08
     Lade
    0.08
     Born
    0.08
     Tig
    0.08
     Geschäft
    0.07
     Bis
    0.07
    Ho
    0.07
    Activations Density 0.002%

    No Known Activations