© 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. 11-RESID-POST-AA
    11. 54767
    Prev
    Next
    INDEX
    Explanations

    iction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivot
    -0.09
     graças
    -0.09
     factoring
    -0.08
     thanks
    -0.08
     honing
    -0.08
     groene
    -0.08
    Pivot
    -0.07
    ковые
    -0.07
    Various
    -0.07
    Earth
    -0.07
    POSITIVE LOGITS
     conflicting
    0.12
     contradictory
    0.09
     incompatible
    0.09
     parece
    0.08
     slightly
    0.08
     Parece
    0.08
     mascota
    0.08
     aparentemente
    0.08
     seems
    0.08
     sembra
    0.08
    Activations Density 0.005%

    No Known Activations