© 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. 108672
    Prev
    Next
    INDEX
    Explanations

    had

    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
     suited
    -0.07
     Треб
    -0.07
     Schutz
    -0.07
     Paths
    -0.07
     Canc
    -0.07
    ிப்ப
    -0.07
    前三
    -0.07
     Pur
    -0.07
     Lingu
    -0.07
     tsp
    -0.07
    POSITIVE LOGITS
     winner
    0.10
    Winner
    0.09
     Winner
    0.09
    伍
    0.09
     victor
    0.08
     realitat
    0.08
    winner
    0.08
     ganador
    0.08
     Primera
    0.08
     recom
    0.08
    Activations Density 0.001%

    No Known Activations