© 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. 68261
    Prev
    Next
    INDEX
    Explanations

    -sion or -ion

    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
    蓝
    -0.09
     bella
    -0.08
     bello
    -0.08
     hochwertige
    -0.08
     blue
    -0.08
     fantast
    -0.08
     Blu
    -0.08
    rose
    -0.08
     moons
    -0.07
     claire
    -0.07
    POSITIVE LOGITS
     Namen
    0.08
    .Stat
    0.08
     Stat
    0.08
     店
    0.08
    .rule
    0.08
    .mainloop
    0.08
     Lager
    0.08
     Fl
    0.08
     Pay
    0.07
    ποί
    0.07
    Activations Density 0.001%

    No Known Activations