Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 88349
    Prev
    Next
    INDEX
    Explanations

    past

    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
    AM
    -0.08
    bis
    -0.08
    میں
    -0.08
    대
    -0.08
    کرد
    -0.08
    laf
    -0.08
    niest
    -0.08
     Lad
    -0.07
    lt
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     гориз
    0.08
     विध
    0.07
     способности
    0.07
     midnight
    0.07
     Venus
    0.07
     orbit
    0.07
     discard
    0.07
     needle
    0.07
     صد
    0.07
     क
    0.07
    Activations Density 0.006%

    No Known Activations