© 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. 3-RESID-POST-AA
    11. 1467
    Prev
    Next
    INDEX
    Explanations

    of

    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
     날
    -0.08
    aken
    -0.07
    ื่
    -0.07
    ively
    -0.07
    som
    -0.07
     जैसा
    -0.07
    ibilidade
    -0.07
    ുന്ന
    -0.07
    ací
    -0.07
     profundo
    -0.07
    POSITIVE LOGITS
     contentious
    0.08
     mondial
    0.08
     catching
    0.08
    -paced
    0.07
     resten
    0.07
     gluc
    0.07
     ME
    0.07
    kinson
    0.07
     glucose
    0.07
    ρθ
    0.07
    Activations Density 0.018%

    No Known Activations