© 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. 29641
    Prev
    Next
    INDEX
    Explanations

    geohashing

    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
     দু
    -0.08
    .Expressions
    -0.08
    frequency
    -0.08
    .An
    -0.07
    Minn
    -0.07
    Tous
    -0.07
     concernés
    -0.07
    ivity
    -0.07
    anol
    -0.07
    amental
    -0.07
    POSITIVE LOGITS
    िलो
    0.08
     bille
    0.08
     democr
    0.08
     dés
    0.08
     enfat
    0.08
    њу
    0.07
     dob
    0.07
     reac
    0.07
     desc
    0.07
    elling
    0.07
    Activations Density 0.001%

    No Known Activations