© 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. 78350
    Prev
    Next
    INDEX
    Explanations

    pipeline

    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
    omon
    -0.07
    望
    -0.07
     Albion
    -0.07
     bacteria
    -0.07
    bug
    -0.07
    .Tag
    -0.07
     Charity
    -0.07
    �
    -0.07
    ाग
    -0.07
     beet
    -0.07
    POSITIVE LOGITS
     INVALID
    0.09
    -invalid
    0.08
    _INVALID
    0.08
     আনন্দ
    0.08
     سار
    0.08
     vähän
    0.08
     ?>
    0.08
     অহ
    0.08
     impost
    0.08
     світ
    0.08
    Activations Density 0.000%

    No Known Activations