© 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. 3-RESID-POST-AA
    11. 12764
    Prev
    Next
    INDEX
    Explanations

    container

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Soc
    -0.08
    Aj
    -0.08
     во
    -0.08
     Soc
    -0.08
     haft
    -0.07
     Tow
    -0.07
     Travis
    -0.07
     বিশ্ব
    -0.07
     Aj
    -0.07
     Lus
    -0.07
    POSITIVE LOGITS
    �
    0.08
     Chem
    0.07
     Gim
    0.07
     ning
    0.07
    tags
    0.07
     Coch
    0.07
     circa
    0.07
    yang
    0.07
     gand
    0.07
    porn
    0.07
    Activations Density 0.007%

    No Known Activations