© 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. 23-RESID-POST-AA
    11. 97271
    Prev
    Next
    INDEX
    Explanations

    rav

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -0.09
    ציה
    -0.08
    דת
    -0.07
    ૈ
    -0.07
    ля
    -0.07
    理
    -0.07
     Adoption
    -0.07
    ляем
    -0.07
    自
    -0.07
    的是
    -0.07
    POSITIVE LOGITS
    vy
    0.15
    enging
    0.13
    elling
    0.12
    enger
    0.11
    emouth
    0.11
    ishments
    0.11
    eler
    0.11
    agers
    0.11
    AGED
    0.10
    erns
    0.10
    Activations Density 0.008%
    No Known Activations