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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119147
    Prev
    Next
    INDEX
    Explanations

    Git

    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
     Welch
    -0.08
     polys
    -0.08
     KC
    -0.08
     अग
    -0.08
     Kaplan
    -0.07
     microw
    -0.07
     Edmund
    -0.07
     способ
    -0.07
     toughness
    -0.07
     occasion
    -0.07
    POSITIVE LOGITS
    lab
    0.10
    LAB
    0.09
     vern
    0.09
    Lab
    0.09
    Hub
    0.08
    NL
    0.08
     Bata
    0.07
     maintaining
    0.07
     sadd
    0.07
     overt
    0.07
    Activations Density 0.002%

    No Known Activations