© 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. 78296
    Prev
    Next
    INDEX
    Explanations

    in

    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
     burgeoning
    -0.08
    -0.08
    mutable
    -0.08
     Muss
    -0.07
     Ducks
    -0.07
    جان
    -0.07
     guerre
    -0.07
     kurt
    -0.07
    把
    -0.07
     Stéph
    -0.07
    POSITIVE LOGITS
    搬
    0.09
    inted
    0.08
    iety
    0.08
    Tie
    0.08
    imest
    0.07
    tie
    0.07
     Roof
    0.07
     मालिक
    0.07
     사
    0.07
     ince
    0.07
    Activations Density 0.006%
    No Known Activations