© 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. 68318
    Prev
    Next
    INDEX
    Explanations

    story

    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
    eker
    -0.08
     ആശ
    -0.07
    Ses
    -0.07
     Heard
    -0.07
    观点
    -0.07
    传
    -0.07
    频道
    -0.07
    738
    -0.07
     chuẩn
    -0.07
    aker
    -0.07
    POSITIVE LOGITS
     모습을
    0.09
    樓
    0.08
     medicines
    0.08
    ності
    0.08
     hoogte
    0.08
     hym
    0.08
     wegge
    0.08
     vertically
    0.08
     Bene
    0.08
     স্ত
    0.08
    Activations Density 0.004%

    No Known Activations