© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113583
    Prev
    Next
    INDEX
    Explanations

    time, starting point

    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
    mediate
    -0.07
     assembler
    -0.07
    sed
    -0.07
     message
    -0.07
     slots
    -0.07
    _enum
    -0.07
     onderhouden
    -0.07
    calc
    -0.07
     synonyms
    -0.07
     arsenal
    -0.07
    POSITIVE LOGITS
     ప్రారంభ
    0.13
     rozpoc
    0.12
     શરૂ
    0.12
     начале
    0.12
     시작
    0.12
     startet
    0.11
     सुरू
    0.11
     нач
    0.11
     iniciar
    0.11
    	start
    0.11
    Activations Density 0.039%

    No Known Activations