© 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. 8081
    Prev
    Next
    INDEX
    Explanations

    amber

    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
    Modulo
    -0.08
     Ded
    -0.07
    NER
    -0.07
     ggf
    -0.07
    Ded
    -0.07
     collider
    -0.07
     ADHD
    -0.07
    מא
    -0.07
    -0.07
    laştır
    -0.07
    POSITIVE LOGITS
     tones
    0.09
    -colored
    0.08
     twists
    0.08
     hues
    0.08
     flame
    0.08
    凤凰
    0.08
    tones
    0.08
     elemental
    0.08
     മുതൽ
    0.07
    指出
    0.07
    Activations Density 0.001%
    No Known Activations