© 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. 7-RESID-POST-AA
    11. 1260
    Prev
    Next
    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     repert
    -0.08
     foods
    -0.08
    Foods
    -0.08
     مواد
    -0.08
     Songs
    -0.08
     receitas
    -0.08
     armazen
    -0.07
     motto
    -0.07
     Schatz
    -0.07
     pengar
    -0.07
    POSITIVE LOGITS
     silhouettes
    0.11
     silhou
    0.11
     silhouette
    0.11
     shimmering
    0.10
     shimmer
    0.10
     blurry
    0.09
     faded
    0.09
     distortion
    0.09
     रंग
    0.08
     चम
    0.08
    Activations Density 0.068%

    No Known Activations