© 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. 99351
    Prev
    Next
    INDEX
    Explanations

    #

    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
     Bon
    -0.10
     �
    -0.08
    Bon
    -0.08
    Poss
    -0.08
     పెట్ట
    -0.07
     Pak
    -0.07
    模
    -0.07
     vork
    -0.07
    Ki
    -0.07
     lei
    -0.07
    POSITIVE LOGITS
     zs
    0.08
    formerly
    0.08
     allá
    0.08
    remember
    0.08
    요일
    0.07
     remember
    0.07
     NES
    0.07
     rappelle
    0.07
     gema
    0.07
    banana
    0.07
    Activations Density 0.002%

    No Known Activations