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. 11-RESID-POST-AA
    6. 44174
    Prev
    Next
    INDEX
    Explanations

    time

    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
    ähr
    -0.08
     sufr
    -0.08
    압
    -0.07
     frustrations
    -0.07
     probs
    -0.07
    비
    -0.07
     amps
    -0.07
     Tamp
    -0.07
     jf
    -0.07
     trapped
    -0.07
    POSITIVE LOGITS
    立即
    0.10
     eagerly
    0.09
    进行了
    0.09
     promptly
    0.09
     agad
    0.09
    いました
    0.09
     enthusiast
    0.08
     самое
    0.08
     indul
    0.08
     اهتمام
    0.08
    Activations Density 0.027%

    No Known Activations