© 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. 12770
    Prev
    Next
    INDEX
    Explanations

    bez

    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
     painless
    -0.09
     shir
    -0.08
    CX
    -0.08
     să
    -0.08
    Bravo
    -0.08
     ast
    -0.07
     divert
    -0.07
    uil
    -0.07
    adol
    -0.07
    以来
    -0.07
    POSITIVE LOGITS
     Cont
    0.08
    Sett
    0.08
     أق
    0.07
    Villa
    0.07
     tubular
    0.07
     عنصر
    0.07
    	element
    0.07
    cont
    0.07
     famille
    0.07
    بر
    0.07
    Activations Density 0.000%

    No Known Activations