© 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. 26449
    Prev
    Next
    INDEX
    Explanations

    common words

    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
    Dtos
    -0.08
     surn
    -0.08
     automate
    -0.08
     जित
    -0.08
     ruin
    -0.07
    	names
    -0.07
     trs
    -0.07
     finir
    -0.07
    	ct
    -0.07
    crt
    -0.07
    POSITIVE LOGITS
     شاشة
    0.09
     affich
    0.09
    /display
    0.08
     hefty
    0.08
     പ്രഖ്യാപ
    0.08
     شعار
    0.08
     déclaré
    0.08
     хәбәр
    0.08
     വയ
    0.08
     slapped
    0.08
    Activations Density 0.029%

    No Known Activations